This repository provides a hands-on exploration of essential Deep Learning concepts using TensorFlow, Keras, and NumPy through a series of curated Jupyter notebooks. It’s designed to help students, practitioners, and AI enthusiasts understand how deep learning models are built, trained, and evaluated.
| Notebook | Description |
|---|---|
ann_basics.ipynb |
Introduction to Artificial Neural Networks (ANNs) |
cnn_classification.ipynb |
Image classification using Convolutional Neural Networks (CNNs) |
activation_functions.ipynb |
Exploration of ReLU, Sigmoid, Tanh, Softmax, etc. |
loss_functions.ipynb |
Comparison of loss functions (MSE, CrossEntropy, etc.) |
optimizers.ipynb |
Working with optimizers like SGD, Adam, RMSProp |
regularization_dropout.ipynb |
Preventing overfitting using dropout and L2 regularization |
mnist_classification.ipynb |
Building a model to classify handwritten digits (MNIST) |
Note: The above file names are assumed; feel free to replace them with your actual notebook names.
- Python 3.8+
- TensorFlow / Keras
- NumPy
- Matplotlib / Seaborn
- Jupyter Notebook
git clone https://github.com/anjaliy11/Deep_Learning.git
cd Deep_Learning