DeepLearning-PadhAI

---

This repository contains the hands-on materials used in the deep learning course by PadhAI.
The course is now available here at Guvi!

Repository Structure

Each folder inside the repo contains the code for the respective topic and has support to execute the code directly in Google colab and/or Kaggle Kernels without worrying about installing the dependencies

Contents of the repository

• Activation Function and Weight Initialization Methods: Analyzing the effect of activations and weight initialisation methods on deep neural network.
  • Blog: Implementing and Analyzing different Activation Functions and Weight Initialization Methods Using Python
• Overfitting and Regularization: concept of overfitting in deep neural networks and how regularization helps to address the problem of overfitting.
  • Blog: Regularization Techniques for Better Neural Network Performance
• PyTorch Intro: Tutorial code for deep learning researchers to learn PyTorch using GPU in Colab.
  • Blog: Getting Started With PyTorch In Google Collab With Free GPU
• Feed-forward NN with Pytorch: Tutorial code for building feedforward neural networks using PyTorch.
  • Blog: Building a Feedforward Neural Network using PyTorch NN Module
• Image Classification Using PyTorch: Building Image classifier using PyTorch on CIFAR10, FashionMNIST datasets
  • Blog: Introduction to Image Classification using PyTorch to Classify FashionMNIST Dataset
• Visualizing CNN Models: Visualizing the filters present in CNN.
  • Blog: Visualizing Convolution Neural Networks using Pytorch
• Batch Normalization and Dropout in Neural Networks: Batch Norm and Dropout explained with PyTorch

Getting Started with code

$ git clone https://github.com/One-Fourth-Labs/DeepLearning-PadhAI.git
$ cd DeepLearning-PadhAI/

Dependencies

• Python 3.5+ & Jupyter Notebook Setup (or just Google Colab)
• PyTorch 0.4.0+

Credits

Thanks to NiranjanKumar for compiling the Padhai-Deeplearning course NoteBooks into a repo!