Skip-gram vs CBOW: Understanding Word2vec Training Examples
A deep dive into how Skip-gram and CBOW generate training examples differently, and why it matters for your dataset size.
Oct 12, 2025
KL Divergence, Cross Entropy
tbd
Oct 12, 2025
Understanding DeepSeek's Multi-Head Latent Attention- One Trillion Dollar Math Trick
A comprehensive mathematical derivation of DeepSeek MLA's weight absorption mechanism, explaining how it compresses the KV cache by 57× while maintaining performance.
Oct 11, 2025
Understanding Normalization in Deep Learning: A Complete Guide
A comprehensive exploration of normalization techniques in neural networks, from basic concepts to advanced comparisons and real-world applications.
Apr 11, 2025