Neural Network Fundamentals

0%

    Normalization Layers

    • LayerNorm Forward and Backward in NumPy

      Mid
    • RMSNorm Forward and Backward Pass

      Mid
    • Fold BatchNorm into a Preceding Linear Layer

      Mid
    • BatchNorm1d Forward and Backward in NumPy

      Senior

    Weight Initialization

    • Xavier and He Weight Initialisation

      Junior

    Layers Backpropagation

    • Fully Connected Linear Layer in NumPy

      Junior
    • Residual Block Forward and Backward Pass

      Mid

    Perceptrons Mlp Basics

    • Perceptron From Scratch: AND, OR and XOR

      Junior
    • Two-Layer NumPy MLP for XOR

      Mid

    Activation Functions

    • ReLU and LeakyReLU Forward and Backward

      Junior
    • GELU and SiLU Activations in NumPy

      Mid

    Memory Parameter Accounting

    • Activation Checkpointing for a Tanh MLP

      Senior

    Autograd Debugging Distributed Training

    • Forward-Mode Autodiff with Dual Numbers

      Mid
    • Scalar Reverse-Mode Autograd Engine

      Senior
    • Simulated Data-Parallel MLP Training with All-Reduce

      Senior
    • Column- and Row-Parallel Linear Layers

      Senior