Deep Learning Overview

andrewtbham1 pts1 comments

GitHub - andrewt3000/MachineLearning: Machine Learning Notes · GitHub

/" data-turbo-transient="true" />

Skip to content

Search/

Sign in<br>Sign upAppearance settings

You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

{{ message }}

andrewt3000

MachineLearning

Public

Notifications<br>You must be signed in to change notification settings

Fork

Star

master

BranchesTags

Go to file

CodeOpen more actions menu

Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit

History<br>778 Commits<br>778 Commits

code

code

img

img

.stats.md.swp

.stats.md.swp

README.md

README.md

calculus.md

calculus.md

cnn.md

cnn.md

cv.md

cv.md

data.md

data.md

gbm.md

gbm.md

la.md

la.md

llm.md

llm.md

machineLearning.md

machineLearning.md

neuralNets.md

neuralNets.md

rl.md

rl.md

rnn.md

rnn.md

stats.md

stats.md

transformer.md

transformer.md

View all files

Repository files navigation

Machine Learning Overview

Basics: stats, linear algebra, calculus

data and features

training neural networks

transformers

LLM

reinforcement learning

Legacy: cnn, rnn

In progress: - vision transformers

Machine Learning is a sub-field of artificial intelligence that uses data to train predictive models.

Training and Inference

Machine learning problems follow a two-phase flow:

Training : The model learns from data — adjusting its parameters to minimize error (supervised learning) or maximize reward (RL). This phase is computationally expensive and done offline.

Inference : The trained model is deployed and makes predictions on new, unseen inputs. Parameters are frozen — the model applies what it learned. This phase must often be fast and cheap, since it runs in production (e.g., serving predictions in real time).

Types of machine learning

Supervised learning - learns from labeled training data.

svm, knn, random forests, gradient boosting machines, neural networks

Unsupervised learning - learns from unlabeled training data.

principal component analysis, clustering.

Reinforcement learning - An agent interacts with an environment and learns to take action by maximizing a cumulative reward .

Q-Learning, Deep Q-Networks (DQN), Proximal Policy Optimization (PPO)

Machine learning problems

Regression - predicting a continuous value attribute.

Example: predicting house prices

Classification - predicting a discrete value.

Classification is further categorized as binary or multi-class classification.

Binary Example: predicting pass or fail, benign or malignant, spam or not spam, hot dog or not hot dog :-)

Multi-Class Example: Handwritten Digit Recognition (0 through 9) mnist, Image classification with 1,000 classes ImageNet-1k

Ranking - predicting the relative order or preference of a set of items contextually.

Example: search engine results, or movie recommendations

Models that predict labels from inputs (as in the problems above) are called discriminative ; models that learn the data distribution to synthesize new samples (diffusion, LLMs) are generative .

Additional Machine learning techniques

Transfer learning is storing knowledge gained while solving one problem and applying it to a different but related problem.

fine tuning is additional training to a base model for a specific task.

LoRA (Low-Rank Adaptation) is a fine-tuning method that freezes the base model's weights and trains small low-rank matrices that are added to existing layers.

Semi-Supervised learning trains on a mix of mostly unlabeled with a small labeled subset data.

Self-supervised learning is a form of unsupervised learning where training labels are constructed automatically from the data itself.

Autoregressive LLM pretraining (next word prediction), and masked image modeling.

Metric learning trains a model to produce embeddings where distance reflects similarity. A siamese network passes two inputs through identical networks with shared weights and compares the resulting embeddings. Trained with contrastive loss (pull matching pairs together, push non-matching pairs apart) or triplet loss (anchor, positive, negative).

Example: face verification, signature verification

Classes

Stanford CS229 Machine Learning

Stanford CS230 Deep Learning - Autumn 2025

Stanford CS231 Deep Learning for Computer Vision - Spring 2025

Stanford CS336 Language Models from scratch - Spring 2025

Stanford CME295 Transformers and LLMs

About<br>Machine Learning Notes<br>Resources<br>Readme<br>Activity<br>Stars<br>0 stars<br>Watchers<br>2 watching<br>Forks<br>0 forks<br>Report repository

Releases

Packages

Used by

Contributors

Languages

You can’t perform that action at this time.

learning data machine training model from

Related Articles