NumPy

Neural network

Python

Logistic Regression

Batch Normalization

Generative adversarial network (GAN)

Shallow Neural Network

Deep Neural Network

Optimization Algorithms

Initialization

Regularization (mathematics)

Gradient Checking

Optimization

Hyperparameter Tuning

TensorFlow

Deep Convolutional Models

Residual Networks

Detection Algorithms

Face Recognition

Neural Style Transfer

You Only Look Once (YOLO)

ConvNets

Image Segmentation

U-Net

Recurrent neural network (RNN)

Long Short-Term Memory (LSTM)

Natural Language Processing (NLP)

Word Embeddings

Attention (machine learning)

Transformer (machine learning model)

Deep Reinforcement Learning

Neural Machine Translation

Trigger Word Detection

Transfer learning

Sequence-to-sequence (Seq2Seq)

CS 230 Deep Learning Stanford University Fall 2022 An in-depth course focused on building neural networks and leading successful machine learning projects. It covers Convolutional Networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more. Students are expected to have basic computer science skills, probability theory knowledge, and linear algebra familiarity.  Deep Learning is one of the most highly sought after skills in AI. In this course, you will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects. You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more.  Students are expected to have the following background, and are invited to take the [Workera](http://www.workera.ai/) technical assessments prior to the class to self-assess themselves prior to taking the class:

- Knowledge of basic computer science principles and skills, at a level sufficient to write a reasonably non-trivial computer program. This corresponds to a Developing level (or badge) in the “Algorithmic Coding” section on [Workera](http://www.workera.ai/).
- Familiarity with the probability theory (CS 109 or STATS 116), which students can assess by taking the “Data Science” section on [Workera](http://www.workera.ai/).
- Familiarity with linear algebra (MATH 51), which students can assess by taking the “Mathematics” section on [Workera](http://www.workera.ai/). 

CS 230 Deep Learning

Deep Learning

Linear Algebra

Gaussian Discriminant Analysis

Support Vector Machine (SVM)

Expectation Maximization

Unsupervised learning

Prompting

Exponential family

Weighted Least Squares

Generalized Linear Models

Kernel (operating system)

Feature / Model Selection

Factor Analysis

Self-supervised Learning

Instruct Tuning

Supervised learning

Newton's Method

Probability

Bias - Variance

Gaussian Mixture Models (GMM)

Independent Component Analysis (ICA)

In-context Learning

Multi-class Classification

Backpropagation

K-means clustering

Principal Component Analysis (PCA)

Large Language Model (LLM)

Reinforcement Learning from Human Feedback (RLHF)

CS 229: Machine Learning Stanford University Winter 2023 This comprehensive course covers various machine learning principles from supervised, unsupervised to reinforcement learning. Topics also touch on neural networks, support vector machines, bias-variance tradeoffs, and many real-world applications. It requires a background in computer science, probability, multivariable calculus, and linear algebra.  This course provides a broad introduction to machine learning and statistical pattern recognition. Topics include: supervised learning (generative/discriminative learning, parametric/non-parametric learning, neural networks, support vector machines); unsupervised learning (clustering, dimensionality reduction, kernel methods); learning theory (bias/variance tradeoffs, practical advice); reinforcement learning and adaptive control. The course will also discuss recent applications of machine learning, such as to robotic control, data mining, autonomous navigation, bioinformatics, speech recognition, and text and web data processing.  Students are expected to have the following background:

- Knowledge of basic computer science principles and skills, at a level sufficient to write a reasonably non-trivial computer program in Python/NumPy. (CS106A or CS106B, CS106X.)
- Familiarity with probability theory. (CS 109, MATH151, or STATS 116) 
- Familiarity with multivariable calculus and linear algebra (relevant classes include, but not limited to MATH 51, MATH 104, MATH 113, CS 205, CME 100.) Stanford Math 51 course text can be found [here](https://web.stanford.edu/class/math51/stanford/math51book.pdf). 

CS 229: Machine Learning

Machine Learning

scikit-image

scikit-learn

pandas (software)

Jupyter Notebook

Code Complexity

Memory management

List (abstract data type)

File Processing

pandas DataFrame

Data Science Libraries

Search

Joins

Images

Statistics

Indexes

Control Structures

Data structure

Data Visualization

Class (computer programming)

Algorithmic Efficiency

Ethics

p-hacking

Tree (data structure)

String (computer science)

Computer file

Machine learning

Object (computer science)

Geospatial Data

Convolution

Algorithmic fairness

Algorithmic Privacy

CSE 163 Intermediate Data Programming University of Washington Summer 2022 This course offers an intermediate level of data programming, focusing on different data types, data science tools, code complexity, and memory management. It emphasizes the efficient use of concepts for data programming. The world has become data-driven. Domain scientists and industry increasingly rely on data analysis to drive innovation and discovery; this reliance on data is not only restricted to science or business, but also is crucial to those in government, public policy, and those wanting to be informed citizens. As the size of data continues to grow, everyone will need to use powerful tools to work with that data.

This course teaches intermediate data programming. It is a follow on to CSE142 (Computer programming I) or CSE160 (Data Programming).

The course complements CSE143, which focuses more deeply on fundamental programming concepts and the internals of data structures. In contrast, CSE163 emphasizes the efficient use of those concepts for data programming.

In this course, students will learn:

1. More advanced programming concepts than in CSE142 or CSE160 including how to write bigger programs with multiple classes and modules.
1. How to work with different types of data: tabular, text, images, geo-spatial.
1. Ecosystem of data science tools including Jupyter Notebook and various data science libraries including scikit image, scikit learn, and Pandas data frames.
1. Basic concepts related to code complexity, efficiency of different types of data structures, and memory management.  This is class is designed as the second introductory programming course that focuses on writing programs that work with data. The prerequisites for the class require students having taken CSE 142 or CSE 160 and the class has been designed to be accessible to students from either of those backgrounds. Students that have taken 143 are welcome to take this class as it will serve as a complement to the material learned in 143 with only minor overlap.

Because this course will have students coming from many different class backgrounds, the first couple of weeks will be pretty different for students depending on what classes they have taken. Here is what we expect students to see in the first weeks based on their background:

- 142: The first two weeks might go pretty fast, but will be doable since you already know all the concepts (loops, conditionals, methods) and you are just learning all the new “words” in Python to use those concepts. This might require a little bit of extra practice early in the quarter so you are familiar with translating all the ideas you have learned in 142 to this new language. The first week has been designed to be a recap of all things 142 so you don’t also have to be learning a ton of new material while learning a new language in the first week.
 - 160: The first week will just be a bit of a review for you, but the class will start covering material you haven’t seen before starting in the second week.
- 143: You are in a similar boat as the 142 students, where you know a lot of the concepts but don’t know the Python language. You’ll probably see a few things that you saw in 143 in this class, but I think the new context of processing data in a new language will still keep it new, exciting, and challenging. 

CSE 163 Intermediate Data Programming

Computer Programming

Data Science

Artificial intelligence

Health care

Medical imaging

Classification

Object detection

3D modeling

Video processing

Electronic health record

Multimodal Data

Multimodal Models

Genomics

Interpretability (machine learning)

Fairness (machine learning)

Ethics of AI and Healthcare

Distributed learning

Differential privacy

k-anonymity

Private aggregation of teacher ensembles (PATE)

Deep learning

Federated learning

Reinforcement learning (RL)

CS 271 / BIOMEDIN 220 Artificial Intelligence in Healthcare Stanford University Fall 2022-2023 Offered by Stanford University, this course focuses on AI applications in healthcare, exploring deep learning models for image, text, multimodal, and time-series data in the healthcare context. Topics also address AI integration challenges like interpretability and privacy. Healthcare is one of the most exciting application domains of artificial intelligence, with transformative potential in areas ranging from medical image analysis to electronic health records-based prediction and precision medicine. This course will involve a deep dive into recent advances in AI in healthcare, focusing in particular on deep learning approaches for healthcare problems. We will start from foundations of neural networks, and then study cutting-edge deep learning models in the context of a variety of healthcare data including image, text, multimodal and time-series data. In the latter part of the course, we will cover advanced topics on open challenges of integrating AI in a societal application such as healthcare, including interpretability, robustness, privacy and fairness. The course aims to provide students from diverse backgrounds with both conceptual understanding and practical grounding of cutting-edge research on AI in healthcare.  Proficiency in Python, or significant experience with a different programming language and ability to self-learn. Python will be used for homework assignments and the course project. Basic familiarity with college calculus (e.g. Math 19 or 41, comfortable taking derivatives), linear algebra (e.g. Math 51 or EE 103 / CME 103, comfortable with common matrix vector operations and notation), and probability and statistics (e.g. CME 106 or CS 109, comfortable with common probability distributions, mean, standard deviation, etc). Familiarity with machine learning, e.g. comfortable with the framework of machine learning and experience training a machine learning model. Familiarity with deep learning is highly recommended, e.g. prior experience training a deep learning model. 

CS 271 / BIOMEDIN 220 Artificial Intelligence in Healthcare

Artificial Intelligence

Interdisciplinary

NumPy

4 courses cover this concept

CS 230 Deep Learning

CS 229: Machine Learning

CSE 163 Intermediate Data Programming

CS 271 / BIOMEDIN 220 Artificial Intelligence in Healthcare