Sequence Models shifted my focus from images to language, audio, and time-dependent data. It connected RNNs and LSTMs to attention and finally to Transformers, which became the bridge toward my current NLP/LLM direction.
I worked through character-level language models, word embeddings, emoji prediction, jazz generation, attention-based translation, Transformer architecture, and trigger-word detection. This gave me both classical sequence modeling and modern attention-based foundations.
This course is one reason I moved toward NLP, Transformers, Hugging Face, LLMs, RAG, and agents as my next major learning direction.
Sequence Models was not just a certificate item. I used it as one layer in a longer path: understand the concept, implement it in code, test it on assignments or notebooks, then connect the idea to future portfolio systems.
Sequence Models shifted my focus from images to language, audio, and time-dependent data. It connected RNNs and LSTMs to attention and finally to Transformers, which became the bridge toward my current NLP/LLM direction. The reason it matters on this page is that it shows the exact stage where my learning moved forward, instead of presenting education as a flat list of names.
The most important layer was not memorizing definitions; it was learning how the course concepts behave when they are turned into working code, trained models, evaluation outputs, and notebooks.
I treated the course as a practical loop: watch the theory, re-implement the assignment logic, inspect outputs, record results, and then keep the code in a public repository as evidence of the learning process.
This course is one reason I moved toward NLP, Transformers, Hugging Face, LLMs, RAG, and agents as my next major learning direction. This page also connects to standalone milestone pages, so the course is not represented only by certificate text; it is represented through the labs, models, notebooks, results, and media produced during the learning path.
I worked through character-level language models, word embeddings, emoji prediction, jazz generation, attention-based translation, Transformer architecture, and trigger-word detection. This gave me both classical sequence modeling and modern attention-based foundations. I also used the course to improve how I explain technical decisions: why a model is chosen, what assumptions it makes, where it fails, and what the next improvement should be. That explanation layer is important because my goal is end-to-end AI engineering, not only passing assignments.
A character-level RNN built from scratch to generate dinosaur names and Shakespeare-style text one character at a time.
Open milestone
A sentence-to-emoji classifier that starts with averaged GloVe vectors and then improves the representation with an LSTM sequence model.
Open milestone
A creative sequence-generation project that trains an LSTM on jazz musical values and then uses an inference model to generate a new solo.
Open milestone
A date-normalization model that uses a seq2seq architecture with attention to translate human-readable dates into YYYY-MM-DD format.
Open milestone
A from-scratch TensorFlow/Keras implementation of the Transformer: positional encoding, masks, scaled dot-product attention, encoder, decoder, and full model.
Open milestone
A wake-word detection project that synthesizes 10-second audio examples, converts them to spectrograms, and trains a Conv1D-GRU model to detect “activate.”
Open milestone