Transformer (machine learning model)

Generative adversarial network (GAN)

Long Short-Term Memory (LSTM)

Recurrent neural network (RNN)

Transfer learning

Optimization

Sequence-to-sequence (Seq2Seq)

Convolutional neural network (CNN)

Neural network

Variational autoencoder (VAE)

Regularization (mathematics)

Attention (machine learning)

Autoencoders

Supervised learning

Classification

Linear regression

Training/Validation/Testing

Perceptron

MNIST

Loss function

Backpropagation

Automatic differentiation

Matrix representation of Neural Networks

Graphics Processor (GPU)

TensorFlow

Multilayer perceptron

Activation Functions

Overfitting

Language Models

Word Embeddings

Feedforward neural network

Gated recurrent unit (GRU)

Machine Translation

Scaling Deep Learning Systems

Interpretation of Neural Networks

Unsupervised learning

Deepfake

Reinforcement learning (RL)

Value iteration

Deep Q-learning

Policy Gradient Methods

Actor-Critic Methods

Graph neural network (GNN)

CSCI 1470/2470 Deep Learning Brown University Spring 2022 Brown University's Deep Learning course acquaints students with the transformative capabilities of deep neural networks in computer vision, NLP, and reinforcement learning. Using the TensorFlow framework, topics like CNNs, RNNs, deepfakes, and reinforcement learning are addressed, with an emphasis on ethical applications and potential societal impacts. Over the past few years, Deep Learning has become a popular area, with deep neural network methods obtaining state-of-the-art results on applications in computer vision (Self-Driving Cars), natural language processing (Google Translate), and reinforcement learning (AlphaGo). These technologies are having transformative effects on our society, including some undesirable ones (e.g. deep fakes).

This course is there to give students a practical understanding of how Deep Learning works, how to implement neural networks, and how to apply them ethically. We introduce students to the core concepts of deep neural networks and survey the techniques used to model complex processes within the contexts of computer vision and natural language processing.

Throughout the course, we emphasize and require students to think critically about potential ethical pitfalls that can result from mis-application of these powerful models. The course is taught using the Tensorflow deep learning framework.
 By the end of this course, you will be able to:

- Learn about the fundamental algorithms that underly all modern deep learning models.
- Implement different types of deep learning models in Tensorflow.
- Think critically about using a deep learning model for a task and its potential societal impact.
- Collaborate with classmates on a team project to apply deep learning models to task of your
choice.
- Communicate your findings (both positive and negative results are encouraged) through pre-
sentations. - A basic programming course: (CSCI 0150, 0170 or 0190)
- A linear algebra course: (CSCI 0530, MATH 0520 or 0540)
- A stats / probability course: (CSCI 0220, 1450, 0450, MATH 1610, APMA 1650 or 1655)

Exceptions may be possible for those missing one of these prerequisites if (a) the student has taken
another course which covers similar material, or if (b) the student will be concurrently taking the
prerequisite. If either of these situations applies to you, use the “Request Override” feature in
Courses@Brown to request an override code (and explain why you believe your situation merits
one). ### Textbook

None required. Students are encouraged to refer to the following textbook, which is available online:

- [Deep Learning](https://www.deeplearningbook.org/), by Ian Goodfellow, Yoshua Bengio, and Aaron Courville.

CSCI 1470/2470 Deep Learning

Computer Vision

Self-supervision

Meta-learning

Fine-tuning

Generative Models

CS 182/282A: Deep Neural Networks UC Berkeley Fall 2022 An advanced course dealing with deep networks in the fields of computer vision, language technology, robotics, and control. It delves into the themes of deep learning, model families, and real-world applications. A strong mathematical background in calculus, linear algebra, probability, optimization, and statistical learning is necessary. Deep Networks have revolutionized computer vision, language technology, robotics and control. They have a growing impact in many other areas of science and engineering, and increasingly, on commerce and society. They do not however, follow any currently known compact set of theoretical principles. In Yann Lecun's words they require "an interplay between intuitive insights, theoretical modeling, practical implementations, empirical studies, and scientific analyses." This is a fancy way of saying “we don’t understand this stuff nearly well enough, but we have no choice but to muddle through anyway.” This course attempts to cover that ground and show you how to muddle through even as we aspire to do more. The goal is to teach a principled course in Deep Learning that serves the diverse needs of our students while also codifying the present understanding of the field. Topics covered may include, but are not limited to:
- Underlying themes of deep learning, including building beyond underlying machine learning concepts like supervised vs unsupervised learning, regression and classification, training/validation/testing, distribution shifts, regularization, the fundamental underlying tradeoffs;
- Defining and training neural networks: features, computation graphs, backpropagation, iterative optimization (SGD, Newton’s Method, Momentum, RMSProp, AdaGrad, Adam), strategies for training (explicit and implicit regularization, batch and layer normalization, weight initialization, gradient clipping, ensembles, dropout), hyperparameter tuning
- Families of contemporary models: fully connected networks, convolutional nets, graph neural nets, recurrent neural nets, transformers
- Problems that utilize neural networks: computer vision, natural language processing, generative models, and others.
- Conducting experiments in a systematic, repeatable way, leveraging and presenting data from experiments to reason about network behavior. This is a graduate-level/advanced undergraduate course about a particular approach to information processing using (simulated) analog circuits where the desired circuit behavior is tuned via optimization involving data since we have no idea how to do hand-tuning at scale. Probabilistic frames are useful to understand what is going on, as well as how we navigate certain design choices. Overall, we expect students to have a strong mathematical background in calculus, linear algebra, probability, optimization, and statistical learning. Berkeley undergraduate courses that can help build maturity include:
- **Calculus**: Math 53 (note: Math 1B or AP Math is not enough)
- **Linear Algebra and Optimization**: EECS 16B and EECS 127/227A is ideal, but EECS 16B alone might be enough if students have complete mastery of that material. Math 110 is also helpful. (note: Math 54 or EECS 16A is required as a minimum, but are not nearly enough.)
- **Probability**: EECS 126, Stat 134, or Stat 140 (note: CS 70 is required at a minimum, but might not be enough for everyone)
- **Statistical Learning**: CS 189/289A or Stat 154 (note: Data 102 is insufficient, even when combined with Data 100.)

*Math 53 and EECS 126 and EECS 127 and CS 189 is the recommended background.*

Prerequisites are not enforced for enrollment, but we encourage you to consider taking some of the classes listed above and save this course for a future semester if you feel shaky on the fundamentals.

The course assumes familiarity with programming in a high-level language with data structures. Homeworks and projects will typically use Python. We encourage you to check out this [tutorial](https://docs.python.org/3/tutorial/) if you haven’t used it before. Students who have taken Berkeley courses like CS 61A and CS 61B are well-prepared for the programming components of the class.

We do not have the staff bandwidth to help students with material that they should have understood before taking this course. If you choose to proceed with this course, you are accepting full responsibility to teach yourself anything in your background that you are missing. We will not be slowing down to accommodate you, and questions pertaining to background material will always have the lowest priority in all course forums. 

CS 182/282A: Deep Neural Networks

K-Nearest Neighbors

Linear Classifiers

Stochastic gradient descent (SGD)

Momentum

AdaGrad

Adam

Learning Rate Schedules

Support Vector Machine (SVM)

Softmax Loss

Multi-layer Perceptron

Higher-level representations

Image Features

Convolution

Pooling

Batch Normalization

AlexNet, VGG, GoogLeNet, ResNet

Data Processing

Weight initialization

Hyperparameter Tuning

Data Augmentation

Feature visualization and inversion

Adversarial Examples

DeepDream and Style Transfer

Single-stage detectors

Two-stage detectors

Semantic/Instance/Panoptic segmentation

Language Modeling

Image Captioning

Object Detection

Self-Attention

Video classification

3D CNNs

Two-stream networks

Multimodal Video Understanding

Pixel RNN, Pixel CNN

Pretext Tasks

Contrastive Learning

Multisensory Supervision

Optical Flow

Stereo Vision

3D Shape Representations

Shape Reconstruction

Neural Implicit Representations

CS231n: Deep Learning for Computer Vision Stanford University Spring 2022 This is a deep-dive into the details of deep learning architectures for visual recognition tasks. The course provides students with the ability to implement, train their own neural networks and understand state-of-the-art computer vision research. It requires Python proficiency and familiarity with calculus, linear algebra, probability, and statistics. Computer Vision has become ubiquitous in our society, with applications in search, image understanding, apps, mapping, medicine, drones, and self-driving cars. Core to many of these applications are visual recognition tasks such as image classification, localization and detection. Recent developments in neural network (aka “deep learning”) approaches have greatly advanced the performance of these state-of-the-art visual recognition systems. This course is a deep dive into the details of deep learning architectures with a focus on learning end-to-end models for these tasks, particularly image classification. During the 10-week course, students will learn to implement and train their own neural networks and gain a detailed understanding of cutting-edge research in computer vision. Additionally, the final assignment will give them the opportunity to train and apply multi-million parameter networks on real-world vision problems of their choice. Through multiple hands-on assignments and the final course project, students will acquire the toolset for setting up deep learning tasks and practical engineering tricks for training and fine-tuning deep neural networks.  - Proficiency in Python  
    All class assignments will be in Python (and use numpy) (we provide a tutorial [here](http://cs231n.github.io/python-numpy-tutorial/) for those who aren't as familiar with Python). If you have a lot of programming experience but in a different language (e.g. C/C++/Matlab/Javascript) you will probably be fine.
- College Calculus, Linear Algebra (e.g. MATH 19 or 41, MATH 51)  
     You should be comfortable taking derivatives and understanding matrix vector operations and notation.
- Basic Probability and Statistics (e.g. CS 109 or other stats course)  
    You should know basics of probabilities, gaussian distributions, mean, standard deviation, etc. 

CS231n: Deep Learning for Computer Vision

Multi-task Learning

PyTorch

Black-box Meta-learning

In-context Learning

Optimization-based Meta-learning

Non-Parametric Few-Shot Learning

Unsupervised pre-training

Task Construction

Large-scale Meta-optimization

Variational Inference

Bayesian Meta-learning

Domain Adaptation

Domain Generalization

Lifelong Learning

CS 330 Deep Multi-Task and Meta Learning Stanford University Fall 2022 This course emphasizes leveraging shared structures in multiple tasks to enhance learning efficiency in deep learning. It provides a thorough understanding of multi-task and meta-learning algorithms with a focus on topics like self-supervised pre-training, few-shot learning, and lifelong learning. Prerequisites include an introductory machine learning course. The course is designed for graduate-level students. While deep learning has achieved remarkable success in many problems such as image classification, natural language processing, and speech recognition, these models are, to a large degree, specialized for the single task they are trained for. This course will cover the setting where there are multiple tasks to be solved, and study how the structure arising from multiple tasks can be leveraged to learn more efficiently or effectively. This includes:

- self-supervised pre-training for downstream few-shot learning and transfer learning
- meta-learning methods that aim to learn efficient learning algorithms that can learn new tasks quickly
- curriculum and lifelong learning, where the problem requires learning a sequence of tasks, leveraging their shared structure to enable knowledge transfer

This is a graduate-level course. By the end of the course, students will be able to understand and implement the state-of-the-art multi-task learning and meta-learning algorithms and be ready to conduct research on these topics.  CS 229 or an equivalent introductory machine learning course is required. 

CS 330 Deep Multi-Task and Meta Learning

Python

NumPy

Logistic Regression

Shallow Neural Network

Deep Neural Network

Optimization Algorithms

Initialization

Gradient Checking

Deep Convolutional Models

Residual Networks

Detection Algorithms

Face Recognition

Neural Style Transfer

You Only Look Once (YOLO)

ConvNets

Image Segmentation

U-Net

Natural Language Processing (NLP)

Deep Reinforcement Learning

Neural Machine Translation

Trigger Word Detection

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 is a type of [*Machine Learning*](/topic/machine-learning) that uses large-scale neurral network to solve real world problems. It has a wide range of applications such as [*Computer Vision*](/topic/computer-vision), [*Natural Language Processing*](/topic/natural-language-processing) (NLP), speech recognition, self-driving cars, etc.

Deep Learning

Computer Science

Deep Learning

Prerequisites

Common concepts