All the code files related to the deep learning course from PadhAI
-
Updated
Apr 13, 2020 - Jupyter Notebook
All the code files related to the deep learning course from PadhAI
AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks
A module for making weights initialization easier in pytorch.
PREDICT THE BURNED AREA OF FOREST FIRES WITH NEURAL NETWORKS
A curated list of awesome deep learning techniques for deep neural networks training, testing, optimization, regularization etc.
Neural_Networks_From_Scratch
How weight initialization affects forward and backward passes of a deep neural network
FloydHub porting of deeplearning.ai course assignments
Neural Networks: Zero to Hero. I completed the tutorial series by Andrej Karpathy
RNN-LSTM: From Applications to Modeling Techniques and Beyond - Systematic Review
Making a Deep Learning Framework with C++
Use ML-FLOW and TensorFlow2.0(Keras) to record all the experiments on the Fashion MNIST dataset.
Neural Network
Playground for trials, attempts and small projects.
This code implements neural network from scratch without using any library
Variance normalising pre-training of neural networks.
Deep Learning with TensorFlow Keras and PyTorch
Data driven initialization for neural network models
Comapring different methods of weight initialization and optimizers using PyTorch
This repository explores the impact of various weight initialization methods on a neural network's performance, comparing zero, random, and He initialization. It includes visualizations of cost function and decision boundaries.
Add a description, image, and links to the weight-initialization topic page so that developers can more easily learn about it.
To associate your repository with the weight-initialization topic, visit your repo's landing page and select "manage topics."