mahaprasad - Robuta Search

https://photogallery.indiatimes.com/events/nagpur/n-kumar-hosts-a-mahaprasad-on-anant-chaturdashi/articleshow/42176237.cms N Kumar hosts a mahaprasad on Anant Chaturdashi - Photogallery N Kumar hosts a mahaprasad on Anant Chaturdashi Photogallery. N Kumar hosts a mahaprasad on Anant Chaturdashi. N Kumar hosts a mahaprasad on Anant Chaturdashi... anant chaturdashi kumar hosts mahaprasad photogallery https://datapecharcha.substack.com/p/llm4n6how-self-attention-works LLM4N6:How self-attention works - by Mahaprasad what k,q,v geometrically mean, WHY behind the formula, tackling tricky questions works by self attention mahaprasad https://datapecharcha.substack.com/p/llm4n5-embeddings-and-postional-encoding LLM4N5: Embeddings and Postional Encoding - by Mahaprasad Setting the stage for transformers, how and why positional encoding work, and what's next? embeddings encoding mahaprasad https://datapecharcha.substack.com/p/llm4n7-upgrading-to-multi-head-attention LLM4N7: Upgrading to Multi-Head Attention - by Mahaprasad One attention head isn't enough, combining multiple heads, and making a panel of experts multi head upgrading attention mahaprasad https://datapecharcha.substack.com/p/llm4n3fixing-a-broken-memory-with LLM4N3:Fixing a broken memory with LSTMs - by Mahaprasad Addressing limitations of RNNs, how LSTMs "remember" across long-range dependencies, and what's next? fixing broken memory mahaprasad https://datapecharcha.substack.com/p/llm4n9-lets-train-our-transformer LLM4N9: Let's train our Transformer - by Mahaprasad playing the training game, predicting next token, cross-entropy loss and more let train transformer mahaprasad