Deep Learning
Machine learning with multi-layer neural networks — the foundation under LLMs, from my IBM coursework to PyTorch models I train myself.
Deep learning trains multi-layer neural networks on large datasets. Convolutional, recurrent and transformer networks are all deep learning models, and it is the foundation under today's LLMs.
How I use it
My deep learning foundation comes from the IBM Generative AI Engineering Professional Certificate professional certificate: Deep Learning Essentials with Keras, Machine Learning with Python (V2), and the PyTorch-based language model courses that lead into Transformers and Fine-Tuning.
In practice, I apply it in my Real-time Data Systems work: I fine-tuned a time-series foundation model (IBM Granite TSPulse) on GPU with PyTorch, and implemented PPO from scratch in PyTorch for Reinforcement Learning in custom simulators.
Why it matters
A working understanding of how neural networks learn — loss, gradients, overfitting and evaluation — makes it easier to judge model behaviour, read model documentation critically, and decide when a problem calls for a model at all.
It is the base layer of the certificate, on which NLP and Transformers are built.