diff --git a/README.md b/README.md index 358c6603..0d4766e8 100644 --- a/README.md +++ b/README.md @@ -27,14 +27,14 @@ In this curriculum, you will learn: What we will not cover in this curriculum: -* Business cases of using **AI in Business**. Consider taking [Introduction to AI for business users](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-57639-dmitryso) learning path on Microsoft Learn, or [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-57639-dmitryso), developed in cooperation with [INSEAD](https://www.insead.edu/). +* Business cases of using **AI in Business**. Consider taking [Introduction to AI for business users](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-cacaste) learning path on Microsoft Learn, or [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-cacaste), developed in cooperation with [INSEAD](https://www.insead.edu/). * **Classic Machine Learning**, which is well described in our [Machine Learning for Beginners Curriculum](http://github.com/Microsoft/ML-for-Beginners) -* Practical AI applications built using **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-57639-dmitryso)**. For this, we recommend that you start with modules Microsoft Learn for [vision](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-57639-dmitryso), [natural language processing](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-57639-dmitryso) and others. -* Specific ML **Cloud Frameworks**, such as [Azure Machine Learning](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-57639-dmitryso) or [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-57639-dmitryso). Consider using [Build and operate machine learning solutions with Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-57639-dmitryso) and [Build and Operate Machine Learning Solutions with Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-57639-dmitryso) learning paths. -* **Conversational AI** and **Chat Bots**. There is a separate [Create conversational AI solutions](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-57639-dmitryso) learning path, and you can also refer to [this blog post](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) for more detail. +* Practical AI applications built using **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-cacaste)**. For this, we recommend that you start with modules Microsoft Learn for [vision](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-cacaste), [natural language processing](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-cacaste) and others. +* Specific ML **Cloud Frameworks**, such as [Azure Machine Learning](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-cacaste) or [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-cacaste). Consider using [Build and operate machine learning solutions with Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-cacaste) and [Build and Operate Machine Learning Solutions with Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-cacaste) learning paths. +* **Conversational AI** and **Chat Bots**. There is a separate [Create conversational AI solutions](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-cacaste) learning path, and you can also refer to [this blog post](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) for more detail. * **Deep Mathematics** behind deep learning. For this, we would recommend [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) by Ian Goodfellow, Yoshua Bengio and Aaron Courville, which is also available online at [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/). -For a gentle introduction to *AI in the Cloud* topics you may consider taking the [Get started with artificial intelligence on Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-57639-dmitryso) Learning Path. +For a gentle introduction to *AI in the Cloud* topics you may consider taking the [Get started with artificial intelligence on Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-cacaste) Learning Path. --- # Content @@ -59,11 +59,11 @@ For a gentle introduction to *AI in the Cloud* topics you may consider taking th Keras/TensorFlow Lab IVComputer Vision - AI Fundamentals: Explore Computer Vision + AI Fundamentals: Explore Computer Vision Microsoft Learn Module on Computer Vision - PyTorch - TensorFlow + PyTorch + TensorFlow 6Intro to Computer Vision. OpenCVTextNotebookLab 7Convolutional Neural Networks
CNN ArchitecturesText
TextPyTorchTensorFlowLab @@ -73,11 +73,11 @@ For a gentle introduction to *AI in the Cloud* topics you may consider taking th 11Object DetectionTextPyTorchTensorFlowLab 12Semantic Segmentation. U-NetTextPyTorchTensorFlow VNatural Language Processing - AI Fundamentals: Explore Natural Language Processing + AI Fundamentals: Explore Natural Language Processing Microsoft Learn Module on Natural Language - PyTorch - TensorFlow + PyTorch + TensorFlow 13Text Representation. Bow/TF-IDFTextPyTorchTensorFlow 14Semantic word embeddings. Word2Vec and GloVeTextPyTorchTensorFlow @@ -92,7 +92,7 @@ For a gentle introduction to *AI in the Cloud* topics you may consider taking th 22Deep Reinforcement LearningTextTensorFlowLab 23Multi-Agent SystemsText VIIAI Ethics -24AI Ethics and Responsible AITextMS Learn: Responsible AI Principles +24AI Ethics and Responsible AITextMS Learn: Responsible AI Principles Extras X1Multi-Modal Networks, CLIP and VQGANTextNotebook @@ -120,7 +120,7 @@ However, if you would like to take the course as a self-study project, we sugges - Visit the [Discussion board](https://github.com/microsoft/AI-For-Beginners/discussions) to "learn out loud". - Chat with other learners [on Gitter](https://gitter.im/Microsoft/ai-for-beginners) or [in Telegram channel](http://t.me/ai_for_beginners). -> For further study, we recommend following these [Microsoft Learn](https://docs.microsoft.com/en-us/users/dmitrysoshnikov-9132/collections/31zgizg2p418yo/?WT.mc_id=academic-57639-dmitryso) modules and learning paths. +> For further study, we recommend following these [Microsoft Learn](https://docs.microsoft.com/en-us/users/dmitrysoshnikov-9132/collections/31zgizg2p418yo/?WT.mc_id=academic-77998-cacaste) modules and learning paths. **Teachers**, we have [included some suggestions](/etc/for-teachers.md) on how to use this curriculum. diff --git a/etc/Mindmap.html b/etc/Mindmap.html index 40d97dfe..e602e96a 100644 --- a/etc/Mindmap.html +++ b/etc/Mindmap.html @@ -20,6 +20,6 @@ - + diff --git a/etc/Mindmap.md b/etc/Mindmap.md index 69f435b9..134f5130 100644 --- a/etc/Mindmap.md +++ b/etc/Mindmap.md @@ -8,7 +8,7 @@ - Bottom-up/Neural - Evolutionary - Synergetic / Emergent AI - - [Microsoft AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-57639-dmitryso) + - [Microsoft AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-cacaste) ## [Sybmbolic AI](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/2-Symbolic/README.md) - Knowledge Representation @@ -26,9 +26,9 @@ ## [Computer Vision](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/4-ComputerVision/README.md) - On MS Learn - - [AI Fundamentals: Explore Computer Vision](https://docs.microsoft.com/learn/paths/explore-computer-vision-microsoft-azure/?WT.mc_id=academic-57639-dmitryso) - - [CV with PyTorch](https://docs.microsoft.com/learn/modules/intro-computer-vision-pytorch/?WT.mc_id=academic-57639-dmitryso) - - [CV with TensorFlow](https://docs.microsoft.com/learn/modules/intro-computer-vision-TensorFlow/?WT.mc_id=academic-57639-dmitryso) + - [AI Fundamentals: Explore Computer Vision](https://docs.microsoft.com/learn/paths/explore-computer-vision-microsoft-azure/?WT.mc_id=academic-77998-cacaste) + - [CV with PyTorch](https://docs.microsoft.com/learn/modules/intro-computer-vision-pytorch/?WT.mc_id=academic-77998-cacaste) + - [CV with TensorFlow](https://docs.microsoft.com/learn/modules/intro-computer-vision-TensorFlow/?WT.mc_id=academic-77998-cacaste) - [Intro to CV. OpenCV](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/4-ComputerVision/06-IntroCV/README.md) - [Convolutional Networks](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/4-ComputerVision/07-ConvNets/README.md) - [CNN Architectures](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md) @@ -42,9 +42,9 @@ ## [Natural Language Processing](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/README.md) - On MS Learn - - [AI Fundamentals: Explore NLP](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-57639-dmitryso) - - [NLP with PyTorch](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-pytorch/?WT.mc_id=academic-57639-dmitryso) - - [NLP with TensorFlow](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-TensorFlow/?WT.mc_id=academic-57639-dmitryso) + - [AI Fundamentals: Explore NLP](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-cacaste) + - [NLP with PyTorch](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-pytorch/?WT.mc_id=academic-77998-cacaste) + - [NLP with TensorFlow](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-TensorFlow/?WT.mc_id=academic-77998-cacaste) - [Text Representation](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/README.md) - Bag of Words - TF/IDF @@ -65,7 +65,7 @@ - [Multi-Agent Systems](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/6-Other/23-MultiagentSystems/README.md) ## [AI Ethics](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/7-Ethics/README.md) - - [MS Learn on Responsible AI](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-57639-dmitryso) + - [MS Learn on Responsible AI](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) ## Extras - [Multimodal Networks](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/X-Extras/X1-MultiModal/README.md) - [CLIP](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/X-Extras/X1-MultiModal/Clip.ipynb) diff --git a/etc/Mindmap.svg b/etc/Mindmap.svg index 6d56245a..0985ef25 100644 --- a/etc/Mindmap.svg +++ b/etc/Mindmap.svg @@ -1 +1 @@ -
VQ-GAN
DALL-E
CLIP
GRU
LSTM
GloVE
Word2Vec
TF/IDF
Bag of Words
NLP with TensorFlow
NLP with PyTorch
AI Fundamentals: Explore NLP
Training Tricks
CNN Architectures
CV with TensorFlow
CV with PyTorch
AI Fundamentals: Explore Computer Vision
Overfitting
TensorFlow
PyTorch
Synergetic / Emergent AI
Evolutionary
Bottom-up/Neural
Top-down/Symbolic
Multimodal Networks
MS Learn on Responsible AI
Multi-Agent Systems
Deep Reinforcement Learning
Genetic Algorithms
Text Generation and GPT
Named Entity Recognition
Transformers and BERT
Generative Recurrent Networks
Recurrent Neural Networks
Language Modeling
Semantic Embeddings
Text Representation
On MS Learn
Segmentation
Object Detection
Style Transfer
Generative Adversarial Networks
Autoencoders and VAEs
Trasnsfer Learning
Convolutional Networks
Intro to CV. OpenCV
On MS Learn
Intro to Frameworks
Multi-Layered Networks
Perceptron
Semantic Web
Ontologies
Expert Systems
Knowledge Representation
Microsoft AI Business School
Approaches to AI
History of AI
AI Definition
Extras
AI Ethics
Other Techniques
Natural Language Processing
Computer Vision
Neural Networks
Sybmbolic AI
Introduction to AI
AI
 \ No newline at end of file +
VQ-GAN
DALL-E
CLIP
GRU
LSTM
GloVE
Word2Vec
TF/IDF
Bag of Words
NLP with TensorFlow
NLP with PyTorch
AI Fundamentals: Explore NLP
Training Tricks
CNN Architectures
CV with TensorFlow
CV with PyTorch
AI Fundamentals: Explore Computer Vision
Overfitting
TensorFlow
PyTorch
Synergetic / Emergent AI
Evolutionary
Bottom-up/Neural
Top-down/Symbolic
Multimodal Networks
MS Learn on Responsible AI
Multi-Agent Systems
Deep Reinforcement Learning
Genetic Algorithms
Text Generation and GPT
Named Entity Recognition
Transformers and BERT
Generative Recurrent Networks
Recurrent Neural Networks
Language Modeling
Semantic Embeddings
Text Representation
On MS Learn
Segmentation
Object Detection
Style Transfer
Generative Adversarial Networks
Autoencoders and VAEs
Trasnsfer Learning
Convolutional Networks
Intro to CV. OpenCV
On MS Learn
Intro to Frameworks
Multi-Layered Networks
Perceptron
Semantic Web
Ontologies
Expert Systems
Knowledge Representation
Microsoft AI Business School
Approaches to AI
History of AI
AI Definition
Extras
AI Ethics
Other Techniques
Natural Language Processing
Computer Vision
Neural Networks
Sybmbolic AI
Introduction to AI
AI
 \ No newline at end of file diff --git a/etc/how-to-run.md b/etc/how-to-run.md index 955009c1..ea791fe0 100644 --- a/etc/how-to-run.md +++ b/etc/how-to-run.md @@ -17,7 +17,7 @@ conda activate ai4beg ### Using Visual Studio Code with Python Extension -Probably the best way to use the curriculum is to open it in [Visual Studio Code](http://code.visualstudio.com/?WT.mc_id=academic-57639-dmitryso) with [Python Extension](https://marketplace.visualstudio.com/items?itemName=ms-python.python&WT.mc_id=academic-57639-dmitryso). +Probably the best way to use the curriculum is to open it in [Visual Studio Code](http://code.visualstudio.com/?WT.mc_id=academic-77998-cacaste) with [Python Extension](https://marketplace.visualstudio.com/items?itemName=ms-python.python&WT.mc_id=academic-77998-cacaste). > **Note**: Once you clone and open the directory in VS Code, it will automatically suggest you to install Python extensions. You would also have to install miniconda as described above. @@ -52,12 +52,12 @@ If you do not want to install Python locally, and have access to some cloud reso ## Running in the Cloud with GPU -Some of the later lessons in this curriculum would greatly benefit from GPU support, because otherwise training will be painfully slow. There are a few options you can follow, especially if you have access to the cloud either through [Azure for Students](https://azure.microsoft.com/free/students/?WT.mc_id=academic-57639-dmitryso), or through your institution: +Some of the later lessons in this curriculum would greatly benefit from GPU support, because otherwise training will be painfully slow. There are a few options you can follow, especially if you have access to the cloud either through [Azure for Students](https://azure.microsoft.com/free/students/?WT.mc_id=academic-77998-cacaste), or through your institution: -* Create [Data Science Virtual Machine](https://docs.microsoft.com/learn/modules/intro-to-azure-data-science-virtual-machine/?WT.mc_id=academic-57639-dmitryso) and connect to it through Jupyter. You can then clone the repo right onto the machine, and start learning. NC-series VMs have GPU support. +* Create [Data Science Virtual Machine](https://docs.microsoft.com/learn/modules/intro-to-azure-data-science-virtual-machine/?WT.mc_id=academic-77998-cacaste) and connect to it through Jupyter. You can then clone the repo right onto the machine, and start learning. NC-series VMs have GPU support. > **Note**: Some subscriptions, including Azure for Students, do not provide GPU support out of the box. You may need to request additional GPU cores through technical support request. -* Create [Azure Machine Learning Workspace](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-57639-dmitryso) and then use Notebook feature there. [This video](https://azure-for-academics.github.io/quickstart/azureml-papers/) shows how to clone a repository into Azure ML notebook and start using it. +* Create [Azure Machine Learning Workspace](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-cacaste) and then use Notebook feature there. [This video](https://azure-for-academics.github.io/quickstart/azureml-papers/) shows how to clone a repository into Azure ML notebook and start using it. You can also use Google Colab, which comes with some free GPU support, and upload Jupyter Notebooks there to execute them one-by-one. diff --git a/lessons/2-Symbolic/README.md b/lessons/2-Symbolic/README.md index 49491f75..aefced6d 100644 --- a/lessons/2-Symbolic/README.md +++ b/lessons/2-Symbolic/README.md @@ -212,7 +212,7 @@ See [FamilyOntology.ipynb](FamilyOntology.ipynb) for an example of using Semanti In most of the cases, ontologies are carefully created by hand. However, it is also possible to **mine** ontologies from unstructured data, for example, from natural language texts. -One such attempt was done by Microsoft Research, and resulted in [Microsoft Concept Graph](https://blogs.microsoft.com/ai/microsoft-researchers-release-graph-that-helps-machines-conceptualize/?WT.mc_id=academic-57639-dmitryso). +One such attempt was done by Microsoft Research, and resulted in [Microsoft Concept Graph](https://blogs.microsoft.com/ai/microsoft-researchers-release-graph-that-helps-machines-conceptualize/?WT.mc_id=academic-77998-cacaste). It is a large collection of entities grouped together using `is-a` inheritance relationship. It allows answering questions like "What is Microsoft?" - the answer being something like "a company with probability 0.87, and a brand with probability 0.75". diff --git a/lessons/3-NeuralNetworks/03-Perceptron/README.md b/lessons/3-NeuralNetworks/03-Perceptron/README.md index ca1c23a7..48d9fcb6 100644 --- a/lessons/3-NeuralNetworks/03-Perceptron/README.md +++ b/lessons/3-NeuralNetworks/03-Perceptron/README.md @@ -74,7 +74,7 @@ In this lesson, you learned about a perceptron, which is a binary classification ## 🚀 Challenge -If you'd like to try to build your own perceptron, try [this lab on Microsoft Learn](https://docs.microsoft.com/en-us/azure/machine-learning/component-reference/two-class-averaged-perceptron?WT.mc_id=academic-57639-dmitryso) which uses the [Azure ML designer](https://docs.microsoft.com/en-us/azure/machine-learning/concept-designer?WT.mc_id=academic-57639-dmitryso). +If you'd like to try to build your own perceptron, try [this lab on Microsoft Learn](https://docs.microsoft.com/en-us/azure/machine-learning/component-reference/two-class-averaged-perceptron?WT.mc_id=academic-77998-cacaste) which uses the [Azure ML designer](https://docs.microsoft.com/en-us/azure/machine-learning/concept-designer?WT.mc_id=academic-77998-cacaste). ## [Post-lecture quiz](https://red-field-0a6ddfd03.1.azurestaticapps.net/quiz/203) diff --git a/lessons/4-ComputerVision/06-IntroCV/README.md b/lessons/4-ComputerVision/06-IntroCV/README.md index 93a2e702..d958437b 100644 --- a/lessons/4-ComputerVision/06-IntroCV/README.md +++ b/lessons/4-ComputerVision/06-IntroCV/README.md @@ -94,7 +94,7 @@ Sometimes, relatively complex tasks such as movement detection or fingertip dete ## 🚀 Challenge -Watch [this video](https://docs.microsoft.com/shows/ai-show/ai-show--2021-opencv-ai-competition--grand-prize-winners--cortic-tigers--episode-32?WT.mc_id=academic-57639-dmitryso) from the AI show to learn about the Cortic Tigers project and how they built a block-based solution to democratize computer vision tasks via a robot. Do some research on other projects like this that help onboard new learners into the field. +Watch [this video](https://docs.microsoft.com/shows/ai-show/ai-show--2021-opencv-ai-competition--grand-prize-winners--cortic-tigers--episode-32?WT.mc_id=academic-77998-cacaste) from the AI show to learn about the Cortic Tigers project and how they built a block-based solution to democratize computer vision tasks via a robot. Do some research on other projects like this that help onboard new learners into the field. ## [Post-lecture quiz](https://red-field-0a6ddfd03.1.azurestaticapps.net/quiz/206) diff --git a/lessons/4-ComputerVision/08-TransferLearning/README.md b/lessons/4-ComputerVision/08-TransferLearning/README.md index 961f396b..4e0f5986 100644 --- a/lessons/4-ComputerVision/08-TransferLearning/README.md +++ b/lessons/4-ComputerVision/08-TransferLearning/README.md @@ -24,7 +24,7 @@ Here are sample features extracted from a picture of a cat by VGG-16 network: ## Cats vs. Dogs Dataset -In this example, we will use a dataset of [Cats and Dogs](https://www.microsoft.com/download/details.aspx?id=54765&WT.mc_id=academic-57639-dmitryso), which is very close to a real-life image classification scenario. +In this example, we will use a dataset of [Cats and Dogs](https://www.microsoft.com/download/details.aspx?id=54765&WT.mc_id=academic-77998-cacaste), which is very close to a real-life image classification scenario. ## ✍️ Exercise: Transfer Learning diff --git a/lessons/4-ComputerVision/08-TransferLearning/TransferLearningTF.ipynb b/lessons/4-ComputerVision/08-TransferLearning/TransferLearningTF.ipynb index 6f3acf02..82c97d9b 100644 --- a/lessons/4-ComputerVision/08-TransferLearning/TransferLearningTF.ipynb +++ b/lessons/4-ComputerVision/08-TransferLearning/TransferLearningTF.ipynb @@ -31,7 +31,7 @@ "source": [ "## Cats vs. Dogs Dataset\n", "\n", - "In this unit, we will solve a real-life problem of classifying images of cats and dogs. For this reason, we will use [Kaggle Cats vs. Dogs Dataset](https://www.kaggle.com/c/dogs-vs-cats), which can also be downloaded [from Microsoft](https://www.microsoft.com/en-us/download/details.aspx?id=54765&WT.mc_id=academic-57639-dmitryso).\n", + "In this unit, we will solve a real-life problem of classifying images of cats and dogs. For this reason, we will use [Kaggle Cats vs. Dogs Dataset](https://www.kaggle.com/c/dogs-vs-cats), which can also be downloaded [from Microsoft](https://www.microsoft.com/en-us/download/details.aspx?id=54765&WT.mc_id=academic-77998-cacaste).\n", "\n", "Let's download this dataset and extract it into `data` directory (this process may take some time!):" ] diff --git a/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md b/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md index 16f6dc81..52217604 100644 --- a/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md +++ b/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md @@ -54,10 +54,10 @@ In this dataset, there is only one class of objects `head`, and for each head, y You can train an object detection model using one of the following ways: -* Using [Azure Custom Vision](https://docs.microsoft.com/azure/cognitive-services/custom-vision-service/quickstarts/object-detection?tabs=visual-studio&WT.mc_id=academic-57639-dmitryso) and it's Python API to programmatically train the model in the cloud. Custom vision will not be able to use more than a few hundred images for training the model, so you may need to limit the dataset. +* Using [Azure Custom Vision](https://docs.microsoft.com/azure/cognitive-services/custom-vision-service/quickstarts/object-detection?tabs=visual-studio&WT.mc_id=academic-77998-cacaste) and it's Python API to programmatically train the model in the cloud. Custom vision will not be able to use more than a few hundred images for training the model, so you may need to limit the dataset. * Using the example from [Keras tutorial](https://keras.io/examples/vision/retinanet/) to train RetunaNet model. * Using [torchvision.models.detection.RetinaNet](https://pytorch.org/vision/stable/_modules/torchvision/models/detection/retinanet.html) build-in module in torchvision. ## Takeaway -Object detection is a task that is frequently required in industry. While there are some services that can be used to perform object detection (such as [Azure Custom Vision](https://docs.microsoft.com/azure/cognitive-services/custom-vision-service/quickstarts/object-detection?tabs=visual-studio&WT.mc_id=academic-57639-dmitryso)), it is important to understand how object detection works and to be able to train your own models. \ No newline at end of file +Object detection is a task that is frequently required in industry. While there are some services that can be used to perform object detection (such as [Azure Custom Vision](https://docs.microsoft.com/azure/cognitive-services/custom-vision-service/quickstarts/object-detection?tabs=visual-studio&WT.mc_id=academic-77998-cacaste)), it is important to understand how object detection works and to be able to train your own models. \ No newline at end of file diff --git a/lessons/5-NLP/13-TextRep/README.md b/lessons/5-NLP/13-TextRep/README.md index d73673e5..7bd63e7c 100644 --- a/lessons/5-NLP/13-TextRep/README.md +++ b/lessons/5-NLP/13-TextRep/README.md @@ -68,6 +68,6 @@ Try some other exercises using bag-of-words and different data models. You might ## Review & Self Study -Practice your skills with text embeddings and bag-of-words techniques on [Microsoft Learn](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-pytorch/?WT.mc_id=academic-57639-dmitryso) +Practice your skills with text embeddings and bag-of-words techniques on [Microsoft Learn](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-pytorch/?WT.mc_id=academic-77998-cacaste) ## [Assignment: Notebooks](assignment.md) diff --git a/lessons/5-NLP/17-GenerativeNetworks/README.md b/lessons/5-NLP/17-GenerativeNetworks/README.md index 06798a68..f6110990 100644 --- a/lessons/5-NLP/17-GenerativeNetworks/README.md +++ b/lessons/5-NLP/17-GenerativeNetworks/README.md @@ -60,7 +60,7 @@ While text generation may be useful in its own right, the major benefits come fr Take some lessons on Microsoft Learn on this topic -* Text Generation with [PyTorch](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-pytorch/6-generative-networks/?WT.mc_id=academic-15963-dmitryso)/[TensorFlow](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-tensorflow/5-generative-networks/?WT.mc_id=academic-15963-dmitryso) +* Text Generation with [PyTorch](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-pytorch/6-generative-networks/?WT.mc_id=academic-77998-cacaste)/[TensorFlow](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-tensorflow/5-generative-networks/?WT.mc_id=academic-77998-cacaste) ## [Post-lecture quiz](https://red-field-0a6ddfd03.1.azurestaticapps.net/quiz/217) diff --git a/lessons/5-NLP/20-LangModels/README.md b/lessons/5-NLP/20-LangModels/README.md index 48f62477..7189e247 100644 --- a/lessons/5-NLP/20-LangModels/README.md +++ b/lessons/5-NLP/20-LangModels/README.md @@ -23,7 +23,7 @@ $$ ## GPT is a Family -GPT is not a single model, but rather a collection of models developed and trained by [OpenAI](http://openai.org). The latest model openly available is [GPT-2](https://huggingface.co/docs/transformers/model_doc/gpt2#openai-gpt2), which has up to 1.5 billion parameters (there are several variations of the model, so you can select one for your tasks that is a good compromise between size/performance). Latest GPT-3 model has up to 175 billion parameters, and is available [as a cognitive service from Microsoft Azure](https://azure.microsoft.com/en-us/services/cognitive-services/openai-service/#overview?WT.mc_id=academic-57639-dmitryso), and as [OpenAI API](https://openai.com/api/). +GPT is not a single model, but rather a collection of models developed and trained by [OpenAI](http://openai.org). The latest model openly available is [GPT-2](https://huggingface.co/docs/transformers/model_doc/gpt2#openai-gpt2), which has up to 1.5 billion parameters (there are several variations of the model, so you can select one for your tasks that is a good compromise between size/performance). Latest GPT-3 model has up to 175 billion parameters, and is available [as a cognitive service from Microsoft Azure](https://azure.microsoft.com/en-us/services/cognitive-services/openai-service/#overview?WT.mc_id=academic-77998-cacaste), and as [OpenAI API](https://openai.com/api/). ## Prompt-based Inference diff --git a/lessons/5-NLP/README.md b/lessons/5-NLP/README.md index 725ce858..6fd834e9 100644 --- a/lessons/5-NLP/README.md +++ b/lessons/5-NLP/README.md @@ -35,7 +35,7 @@ pip install -r requirements-torch.txt pip install -r requirements-tf.txt ``` -> You can try NLP with TensorFlow on [Microsoft Learn](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-tensorflow/?WT.mc_id=academic-57639-dmitryso) +> You can try NLP with TensorFlow on [Microsoft Learn](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-tensorflow/?WT.mc_id=academic-77998-cacaste) ## GPU Warning diff --git a/lessons/6-Other/22-DeepRL/README.md b/lessons/6-Other/22-DeepRL/README.md index f5c631d0..fa6755dc 100644 --- a/lessons/6-Other/22-DeepRL/README.md +++ b/lessons/6-Other/22-DeepRL/README.md @@ -90,7 +90,7 @@ Reinforcement Learning nowadays is a fast growing field of research. Some of the * Teaching a computer to play **Atari Games**. The challenging part in this problem is that we do not have simple state represented as a vector, but rather a screenshot - and we need to use the CNN to convert this screen image to a feature vector, or to extract reward information. Atari games are available in the Gym. * Teaching a computer to play board games, such as Chess and Go. Recently state-of-the-art programs like **Alpha Zero** were trained from scratch by two agents playing against each other, and improving at each step. -* In industry, RL is used to create control systems from simulation. A service called [Bonsai](https://azure.microsoft.com/services/project-bonsai/?WT.mc_id=academic-57639-dmitryso) is specifically designed for that. +* In industry, RL is used to create control systems from simulation. A service called [Bonsai](https://azure.microsoft.com/services/project-bonsai/?WT.mc_id=academic-77998-cacaste) is specifically designed for that. ## Conclusion diff --git a/lessons/7-Ethics/README.md b/lessons/7-Ethics/README.md index 9a6a7278..247eba48 100644 --- a/lessons/7-Ethics/README.md +++ b/lessons/7-Ethics/README.md @@ -10,7 +10,7 @@ The kind of AI that we have learned about in this course is nothing more than la ## Principles of Responsible AI -To avoid this accidental or purposeful misuse of AI, Microsoft states the important [Principles of Responsible AI](https://www.microsoft.com/ai/responsible-ai?WT.mc_id=academic-57639-dmitryso). The following concepts underpin these principles: +To avoid this accidental or purposeful misuse of AI, Microsoft states the important [Principles of Responsible AI](https://www.microsoft.com/ai/responsible-ai?WT.mc_id=academic-77998-cacaste). The following concepts underpin these principles: * **Fairness** is related to the important problem of *model biases*, which can be caused by using biased data for training. For example, when we try to predict the probability of getting a software developer job for a person, the model is likely to give higher preference to males - just because the training dataset was likely biased towards a male audience. We need to carefully balance training data and investigate the model to avoid biases, and make sure that the model takes into account more relevant features. * **Reliability and Safety**. By their nature, AI models can make mistakes. A neural network returns probabilities, and we need to take it into account when making decisions. Every model has some precision and recall, and we need to understand that to prevent harm that wrong advice can cause. @@ -31,10 +31,10 @@ Microsoft has developed the [Responsible AI Toolbox](https://github.com/microsof - EconML - tool for Causal Analysis, which focuses on what-if questions - DiCE - tool for Counterfactual Analysis allows you to see which features need to be changed to affect the decision of the model -For more information about AI Ethics, please visit [this lesson](https://github.com/microsoft/ML-For-Beginners/tree/main/1-Introduction/3-fairness?WT.mc_id=academic-57639-dmitryso) on the Machine Learning Curriculum which includes assignments. +For more information about AI Ethics, please visit [this lesson](https://github.com/microsoft/ML-For-Beginners/tree/main/1-Introduction/3-fairness?WT.mc_id=academic-77998-cacaste) on the Machine Learning Curriculum which includes assignments. ## Review & Self Study -Take this [Learn Path](https://docs.microsoft.com/learn/modules/responsible-ai-principles/?WT.mc_id=academic-57639-dmitryso) to learn more about responsible AI. +Take this [Learn Path](https://docs.microsoft.com/learn/modules/responsible-ai-principles/?WT.mc_id=academic-77998-cacaste) to learn more about responsible AI. ## [Post-lecture quiz](https://white-water-09ec41f0f.azurestaticapps.net/quiz/6/) diff --git a/translations/README.ja.md b/translations/README.ja.md index ff0adbfb..7d2f45b1 100644 --- a/translations/README.ja.md +++ b/translations/README.ja.md @@ -27,14 +27,14 @@ 本カリキュラムで扱わない内容 -* **AIをビジネスで活用するためのビジネスケース**。Microsoft Learnの学習パス[ビジネスユーザーのためのAI入門](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-57639-dmitryso)や、[INSEAD](https://www.insead.edu/)と共同で開発した[AIビジネススクール](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-57639-dmitryso)の受講をご検討ください。 +* **AIをビジネスで活用するためのビジネスケース**。Microsoft Learnの学習パス[ビジネスユーザーのためのAI入門](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-cacaste)や、[INSEAD](https://www.insead.edu/)と共同で開発した[AIビジネススクール](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-cacaste)の受講をご検討ください。 * **古典的な機械学習**については、[初心者のための機械学習カリキュラム](http://github.com/Microsoft/ML-for-Beginners)で十分に説明されています。 -* **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-57639-dmitryso)** を利用して構築された実践的なAIアプリケーション。これには、Microsoft Learnの[ビジョン](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-57639-dmitryso)、[自然言語処理](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-57639-dmitryso)などのモジュールから始めることをお勧めします。 -* [Azure Machine Learning](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-57639-dmitryso) や [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-57639-dmitryso) などの特定のML **Cloud Frameworks** を利用する [Azure Machine Learning による機械学習ソリューションの構築と運用](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-57639-dmitryso)、[Azure Databricksによる機械学習ソリューションの構築と運用](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-57639-dmitryso) の学習パスの利用を検討します。 -* **会話型AI**と**Chat Bots**。別途、[Create conversational AI solutions](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-57639-dmitryso) という学習パスがあり、詳しくは[こちらのブログ](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) も参照してください。 +* **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-cacaste)** を利用して構築された実践的なAIアプリケーション。これには、Microsoft Learnの[ビジョン](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-cacaste)、[自然言語処理](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-cacaste)などのモジュールから始めることをお勧めします。 +* [Azure Machine Learning](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-cacaste) や [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-cacaste) などの特定のML **Cloud Frameworks** を利用する [Azure Machine Learning による機械学習ソリューションの構築と運用](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-cacaste)、[Azure Databricksによる機械学習ソリューションの構築と運用](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-cacaste) の学習パスの利用を検討します。 +* **会話型AI**と**Chat Bots**。別途、[Create conversational AI solutions](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-cacaste) という学習パスがあり、詳しくは[こちらのブログ](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) も参照してください。 * **ディープラーニングの背後にある深層数学**。これについては、Ian Goodfellow、Yoshua Bengio、Aaron Courvilleによる[Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618)をお勧めします。また、[https://www.deeplearningbook.org/](https://www.deeplearningbook.org/) で公開されています。 -クラウドにおける*AI*のトピックを優しく紹介するために、[Get started with artificial intelligence on Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-57639-dmitryso) Learning Pathの受講を検討してもよいでしょう。 +クラウドにおける*AI*のトピックを優しく紹介するために、[Get started with artificial intelligence on Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-cacaste) Learning Pathの受講を検討してもよいでしょう。 --- # コンテンツ @@ -59,11 +59,11 @@ Keras/TensorFlow Lab IVコンピュータビジョン - AIファンダメンタルズ コンピュータビジョンの探求 + AIファンダメンタルズ コンピュータビジョンの探求 Microsoft Learn Module - コンピュータビジョン - PyTorch - TensorFlow + PyTorch + TensorFlow 6コンピュータビジョン入門 OpenCVTextNotebookLab 7畳み込みニューラルネットワーク
CNN アーキテクチャText
TextPyTorchTensorFlowLab @@ -73,11 +73,11 @@ 11オブジェクト検出TextPyTorchTensorFlowLab 12セマンティック・セグメンテーション U-NetTextPyTorchTensorFlow V自然言語処理 - AIファンダメンタルズ 自然言語処理の探究 + AIファンダメンタルズ 自然言語処理の探究 Microsoft Learn Module - 自然言語 - PyTorch - TensorFlow + PyTorch + TensorFlow 13文書表現 Bow/TF-IDFTextPyTorchTensorFlow 14セマンティックな単語の埋め込み Word2Vec と GloVeTextPyTorchTensorFlow @@ -92,7 +92,7 @@ 22深層強化学習TextTensorFlowLab 23マルチエージェントシステムText VIIAI倫理 -24AI 倫理と責任ある AI のあり方TextMS Learn: Responsible AI Principles +24AI 倫理と責任ある AI のあり方TextMS Learn: Responsible AI Principles Extras X1マルチモーダルネットワーク、CLIP、VQGANTextNotebook @@ -121,7 +121,7 @@ - [議論ボード](https://github.com/microsoft/AI-For-Beginners/discussions)にアクセスして「大きく声を出して」学ぼう - 他の学習者と [Gitter](https://gitter.im/Microsoft/ai-for-beginners) または [Telegram チャンネル](http://t.me/ai_for_beginners)でチャットすることができます。 -> さらに学習を進めるには、以下の [Microsoft Learn](https://docs.microsoft.com/en-us/users/dmitrysoshnikov-9132/collections/31zgizg2p418yo/?WT.mc_id=academic-57639-dmitryso) のモジュールとラーニングパスに沿って学習することをお勧めします。 +> さらに学習を進めるには、以下の [Microsoft Learn](https://docs.microsoft.com/en-us/users/dmitrysoshnikov-9132/collections/31zgizg2p418yo/?WT.mc_id=academic-77998-cacaste) のモジュールとラーニングパスに沿って学習することをお勧めします。 **先生方**、このカリキュラムをどのように使うかのいくつかの提案](/etc/for-teachers.md)を参考にしてください。