(Day 60) Stanford CS224N (NLP with DL) - Language modelling, RNNs and LSTMs
March 1, 2024
Hello :) Today is Day 60!
A quick summary of today:
- Covered lecture 5 and 6 from CS224N
- Attempted assignment 3 - Neural Transition-Based Dependency Parsing
(Day 59) Stanford CS224N (NLP with DL) - Backprop and Dependency Parsing
February 29, 2024
Hello :) Today is Day 59!
A quick summary of today:
- Lecture 3 of CS224N: backprop and neural nets
- Lecture 4 of CS224N: dependency parsing
(Day 58) Stanford CS224N (NLP with DL) Lecture 2 - Neural classifiers (diving deeper into word embeddings)
February 28, 2024
Hello :) Today is Day 58!
A quick summary of today:
- covered Lecture 2 of Stanford’s NLP with DL
- did assignment 1 on google colab which covered some exercises on count-based and prediction-based methods
- Read 6 papers about word embeddings and wrote down some basic summaries
- GloVe: Global Vectors for Word Representation
- Improving Distributional Similarity with Lessons Learned from Word Embeddings
- Evaluation methods for unsupervised word embeddings
- A Latent Variable Model Approach to PMI-based Word Embeddings
- Linear Algebraic Structure of Word Senses, with Applications to Polysemy
- On the Dimensionality of Word Embedding
(Day 57) Stanford CS224N - Lecture 1. Word vectors
February 27, 2024
Hello :) Today is Day 57!
A quick summary of today:
- Got introduced to word vectors with lecture 1 + small showcase
- Read the paper and took notes about:
- Efficient Estimation of Word Representations in Vector Space (word2vec)
- Distributed Representations of Words and Phrases and their Compositionality (negative sampling)
(Day 56) I found my next step in the ladder - cs224n NLP with DL by Stanford
February 26, 2024
Hello :) Today is Day 56!
A quick summary of today:
- Looked at Natural Language Processing with Transformers
- Found Stanford Uni’s cs224n NLP with DL course
(Day 55) Learning about tokenization in LLMs
February 25, 2024
Hello :) Today is Day 55!
A quick summary of today:
- continuing on the Andrej Karpathy streak from the last few days, today I watched his latest video about tokenization in LLMs
- I used a pokemon name dataset on yesterday’s MLP code (with the manual backprop) and posted it on Kaggle for easier access