Natural Language Processing
Text tokenization, word embeddings (Word2Vec/GloVe), Recurrent Neural Networks (LSTM/GRU), Transformer architecture, and LLM fine-tuning.
Stemming, lemmatization, N-grams, TF-IDF vector matrices, Byte-Pair Encoding (BPE) tokenization.
Text Preprocessing, Tokenization & Vectorization
Stemming, lemmatization, N-grams, TF-IDF vector matrices, Byte-Pair Encoding (BPE) tokenization.
Word2Vec (CBOW/Skip-gram), GloVe, Recurrent Neural Networks (RNN), LSTM memory gates, and GRU.
Word Embeddings & Recurrent Neural Networks
Word2Vec (CBOW/Skip-gram), GloVe, Recurrent Neural Networks (RNN), LSTM memory gates, and GRU.
Scaled dot-product self-attention, Multi-Head Attention, positional encodings, and Transformer Encoders/Decoders.
Transformer Architecture & Self-Attention Mechanics
Scaled dot-product self-attention, Multi-Head Attention, positional encodings, and Transformer Encoders/Decoders.
Pre-trained models (BERT/GPT), LoRA parameter-efficient fine-tuning, RAG vector search, and RLHF alignment.
Large Language Models (LLMs) & Fine-Tuning
Pre-trained models (BERT/GPT), LoRA parameter-efficient fine-tuning, RAG vector search, and RLHF alignment.