From c1b62a5b05ff8f4907708ad097645d187b1f9d8c Mon Sep 17 00:00:00 2001 From: Adarsh Kumar <45385384+AdarshKumar712@users.noreply.github.com> Date: Thu, 16 Jan 2020 20:42:49 +0530 Subject: [PATCH 1/3] Create Readme.md --- text/char-rnn/Readme.md | 4 ++++ 1 file changed, 4 insertions(+) create mode 100644 text/char-rnn/Readme.md diff --git a/text/char-rnn/Readme.md b/text/char-rnn/Readme.md new file mode 100644 index 000000000..1fa2f845a --- /dev/null +++ b/text/char-rnn/Readme.md @@ -0,0 +1,4 @@ +# Character Level Language Model using RNNs +This is an implementation of RNN based Character Level Language Model. In this model,RNN model(based on LSTMs) is given a chunk of huge text on which it is trained to model the probability distribution of the next character in the sequence given a sequence of previous characters. This will then allow the model to generate new text one character at a time + +To train this Model, Shakespeare.txt was used, however any text can be used to train the model. From a8e9697cb17f863a0b8e79d92456170ede7154d6 Mon Sep 17 00:00:00 2001 From: Adarsh Kumar <45385384+AdarshKumar712@users.noreply.github.com> Date: Thu, 16 Jan 2020 21:14:35 +0530 Subject: [PATCH 2/3] Create Readme.md --- vision/mnist/Readme.md | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 vision/mnist/Readme.md diff --git a/vision/mnist/Readme.md b/vision/mnist/Readme.md new file mode 100644 index 000000000..c3f4ab5f9 --- /dev/null +++ b/vision/mnist/Readme.md @@ -0,0 +1,9 @@ +# Simple NN models for Computer Vision on MNIST Dataset +This folder contains following models implemented on MNIST Dataset for Hand-Written Digit Recognition: +1. Simple Multi-layered Perceptron model(mlp.jl) +2. Simple Convolutional Neural Networks(conv.jl) +3. Simple Autoencoders(autoencoder.jl) +4. Variational Autoencoders(vae) + +## About MNIST Dataset +MNIST Dataset is a large database of Handwritten Digits that is commonly used for training various Image Processing Systems From 53725cb5bc232caa357bb93597ac363f4e11e673 Mon Sep 17 00:00:00 2001 From: Adarsh Kumar <45385384+AdarshKumar712@users.noreply.github.com> Date: Thu, 16 Jan 2020 21:21:35 +0530 Subject: [PATCH 3/3] Update Readme.md --- text/char-rnn/Readme.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/text/char-rnn/Readme.md b/text/char-rnn/Readme.md index 1fa2f845a..da98bc43c 100644 --- a/text/char-rnn/Readme.md +++ b/text/char-rnn/Readme.md @@ -1,4 +1,4 @@ # Character Level Language Model using RNNs This is an implementation of RNN based Character Level Language Model. In this model,RNN model(based on LSTMs) is given a chunk of huge text on which it is trained to model the probability distribution of the next character in the sequence given a sequence of previous characters. This will then allow the model to generate new text one character at a time -To train this Model, Shakespeare.txt was used, however any text can be used to train the model. +To train this Model, Shakespeare.txt was used. However, any text can also be used to train the model.