03writing & teaching
the blog
deep dives on machine learning, nlp, llms and operating systems — worked through by hand, with the math and the pictures.
technical blogs 20
- 01 system design, visually63 infographic slides covering system-design foundations, trade-offs, data, messaging, and recovery
- 02 week 1 — linear regressiona deep dive into linear regression and the math behind it
- 03 week 2 — transformersa deep dive into transformers and a visual guide into how it works
- 04 week 3 — optimizersa deep dive into optimizers and a journey through time
- 05 week 4 — rnna deep dive into recurrent neural networks and how the math behind it works
- 06 week 5 — basics of nlp [part 1]text preprocessing, regex, frequencies, and word embeddings
- 07 week 6 — basics of nlp [part 2]pos tagging, ner, sentiment analysis, and n-gram models
- 08 week 7 — basics of nlp [part 3]hidden markov models, text clustering, and attention
- 09 week 8 — llms [part 1]embeddings, positional embeddings, and tokenizers (especially bpe)
- 10 week 9 — enhance your model [part 1]lora, model distillation, gradient clipping and early stopping
- 11 week 10 — llms [part 2]how attention works, in great detail
- 12 deepseek r1 explanationhow deepseek r1 works under the hood
- 13 all about quantizationhow quantization occurs in llms
- 14 training translation models on low-resource languageshow to train translation models on low-resource languages
- 15 what is kl divergenceunderstanding kl divergence and its applications in machine learning
- 16 how does virtual memory even work?virtual memory, page tables, tlbs, page faults, and copy-on-write
- 17 how does interprocess communication work?pipes, message queues, shared memory, and synchronization
- 18 how does dynamic memory allocation work?the heap, malloc, free, and allocator internals
- 19 how do keyword spotting models work?audio features, neural networks, training, and continuous detection
- 20 turboquanthow polarquant and quantized johnson-lindenstrauss combine to achieve 3-bit kv-cache compression with zero memory overhead
guides 7
experience write-ups, hosted on medium and notion.
- 01 how to get into cshow to have a productive 1st year by exploring fields in cs and balancing academics.
- 02 how to get into mlthe foundational stages of learning machine learning — master each step before advancing.
- 03 how i landed a winter intern in 9 monthsmy journey in 2024.
- 04 how to ace your nlp interviewsquestions and answers you can face during an nlp interview.
- 05 how i wrote my first research paperthe process behind my first research paper.
- 06 how i got an on-campus internship: full prep processhow i got an on-campus internship at cisco.
- 07 0 to 1 in nlp & llmsa comprehensive guide for beginners to get started with nlp and llms.