diff --git a/.gitignore b/.gitignore
index 073a0c9..19dbc18 100644
--- a/.gitignore
+++ b/.gitignore
@@ -5,4 +5,6 @@ __pycache__
 
 **/.DS_Store
 
-notebooks/
\ No newline at end of file
+notebooks/
+
+.idea/
\ No newline at end of file
diff --git a/models/Perceptron.py b/models/Perceptron.py
new file mode 100644
index 0000000..d74af1c
--- /dev/null
+++ b/models/Perceptron.py
@@ -0,0 +1,34 @@
+import streamlit as st
+from sklearn.linear_model import Perceptron
+
+
+def lp_param_selector():
+    eta0 = st.slider("learning_rate", 0.001, 10.0, step=0.001, value=1.0)
+    max_iter = st.number_input("max_iter", 100, 2000, step=50, value=100)
+
+    penalty = st.selectbox("penalty", options=["None", "l2", "l1", "elasticnet"])
+
+    if penalty in ["l2", "l1", "elasticnet"]:
+        alpha = st.slider("alpha", 0.00001, 0.001, step=0.00001, value=0.0001)
+    else:
+        alpha = 0.0001
+
+    early_stopping = st.checkbox('early_stopping', value=False)
+
+    if early_stopping:
+        validation_fraction = st.number_input("validation_fraction", 0.0, 1.0, step=0.05, value=0.1)
+        n_iter_no_change = st.number_input("n_iter_no_change", 2, 100, step=1, value=5)
+    else:
+        validation_fraction = 0.1
+        n_iter_no_change = 5
+
+    params = {"eta0": eta0, 
+              "max_iter": max_iter, 
+              "penalty": penalty, 
+              "alpha": alpha, 
+              "early_stopping": early_stopping,
+              "validation_fraction": validation_fraction, 
+              "n_iter_no_change": n_iter_no_change}
+
+    model = Perceptron(**params)
+    return model
diff --git a/models/utils.py b/models/utils.py
index 85316bc..9b6446b 100644
--- a/models/utils.py
+++ b/models/utils.py
@@ -7,6 +7,7 @@
     "K Nearest Neighbors": "from sklearn.neighbors import KNeighborsClassifier",
     "Gaussian Naive Bayes": "from sklearn.naive_bayes import GaussianNB",
     "SVC": "from sklearn.svm import SVC",
+    "Perceptron": "from sklearn.linear_model import Perceptron",
 }
 
 
@@ -19,6 +20,7 @@
     "K Nearest Neighbors": "https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsClassifier.html",
     "Gaussian Naive Bayes": "https://scikit-learn.org/stable/modules/naive_bayes.html",
     "SVC": "https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html",
+    "Perceptron": "https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Perceptron.html",
 }
 
 
@@ -63,4 +65,10 @@
         - They provide different type of kernel functions
         - They require careful normalization   
     """,
+    "Perceptron": """
+        - Perceptron is the simples form of Artificial Neural Network
+        - Single-layer Perceptrons require linearly separable data, otherwise it does not converge
+        - Multilayer Perceptrons (MLP) are feedforward neural networks with two or more layers which have the greater 
+        processing power and can process non-linearly separable data. 
+    """,
 }
diff --git a/utils/ui.py b/utils/ui.py
index 42ee2f0..df27578 100644
--- a/utils/ui.py
+++ b/utils/ui.py
@@ -10,6 +10,7 @@
 from models.KNearesNeighbors import knn_param_selector
 from models.SVC import svc_param_selector
 from models.GradientBoosting import gb_param_selector
+from models.Perceptron import lp_param_selector
 
 from models.utils import model_imports
 from utils.functions import img_to_bytes
@@ -83,6 +84,7 @@ def model_selector():
                 "K Nearest Neighbors",
                 "Gaussian Naive Bayes",
                 "SVC",
+                "Perceptron",
             ),
         )
 
@@ -110,6 +112,9 @@ def model_selector():
         elif model_type == "Gradient Boosting":
             model = gb_param_selector()
 
+        elif model_type == "Perceptron":
+            model = lp_param_selector()
+
     return model_type, model