How aaryan-sharmaa/deep-learning-101 works
Deep Learning 101 is a hands-on learning repository organized around notebook-based study, rather than a deployed application or reusable runtime package. Its visible learning path covers neural-network fundamentals, optimization and training, and PyTorch, with examples ranging from perceptrons and backpropagation to Fashion-MNIST training. The README also lists CNNs, RNNs/LSTMs, attention/transformers, and embeddings as roadmap topics, but the supplied tree contains no corresponding materials. No source excerpts were provided, so relationships below reflect only the documented learning focus.
Main entry points: ANN-Implementations ANN Applications · Backpropagation Backpropagation · Perceptron Perceptrons · Vanishing-Gradient Vanishing Gradient
Components 11
Network Fundamentals
- ANN Applications
01-Neural-Network-Fundamentals/ANN-Implementations - Backpropagation
01-Neural-Network-Fundamentals/Backpropagation - Perceptrons
01-Neural-Network-Fundamentals/Perceptron - Vanishing Gradient
01-Neural-Network-Fundamentals/Vanishing-Gradient
Optimization & Training
- Dropout
02-Optimization-and-Training/Dropout - Training Methods
02-Optimization-and-Training
PyTorch Learning
- Tensors & Autograd
03-PyTorch - Training Pipelines
03-PyTorch - Data Loading
03-PyTorch - Fashion-MNIST
03-PyTorch
Other components
- Learner
Connections 10
- Learner → ANN Applications: studies
README.md - Learner → Backpropagation: studies
README.md - Learner → Perceptrons: studies
README.md - Learner → Vanishing Gradient: studies
README.md - Learner → Dropout: studies
README.md - Learner → Training Methods: studies
README.md - Learner → Tensors & Autograd: studies
README.md - Learner → Training Pipelines: studies
README.md - Learner → Data Loading: studies
README.md - Learner → Fashion-MNIST: studies
README.md