Home
Posts
Notes
Blogs
Notes
Structured Notes, categorized
Backpropagation
Manual Backpropagation On Tensors
Backpropagation From Scratch
Loss function
Maximum Likelihood Estimate As Loss
Why We Need Regularization
Optimization
Rmsnorm
Skip Connections
Optimization Algorithms
Diagnostic Tool While Training Nn
Optimizing Loss
Batchnormalization
Training
Misc
Matrix Visualization
Architecture Implementation
Multi Head Latent Attention
Lora
Kv Cache Gqa
Rope
Mixture Of Experts
Gpt Implementation
GPU
Gpus
Interpretability
Interpretability