$ show MITDeepLearning/introtodeeplearning
This repository contains educational labs for MIT's Introduction to Deep Learning course (6.S191). It consists of Jupyter notebooks covering deep learning fundamentals (Lab1: music generation with RNNs), computer vision (Lab2: MNIST classification and facial detection with VAEs), and LLM fine-tuning (Lab3: style adaptation using LoRA). The repository also includes extra labs for reinforcement learning and uncertainty quantification. While structured as educational material, the labs involve substantive data processing, model training, and evaluation pipelines. The mitdeeplearning package provides reusable utilities for training visualization and data handling. The code assumes execution in Google Colab with GPU access and relies on external APIs (Comet ML, OpenRouter) and datasets hosted on third-party services (Dropbox).
The LLM identified 1 files worth highlighting for reuse:
Provides reusable utility functions for deep learning experimentation: LossHistory (smoothed loss tracking), PeriodicPlotter (dynamic training visualization), create_grid_of_images (image batch visualization), and model display helpers. These abstractions reduce boilerplate across labs and demonstrate skill in creating helpful development tools for interactive environments. While dependent on matplotlib and numpy, they are sufficiently decoupled to be extracted for similar use cases.