BERT

Convolutional neural network (CNN)

Deep Reinforcement Learning

Generative adversarial network (GAN)

Image Classification

Machine learning

Network Architectures

Neural network

Optimization

Optimizers

Segmentation and Detection

Sequential Data

Transformer (machine learning model)

CSE 490 G1 / 599 G1 Introduction to Deep Learning University of Washington Autumn 2019 A survey course on neural network implementation and applications, including image processing, classification, detection, and segmentation. The course also covers semantic understanding, translation, and question-answering applications. It's ideal for those with a background in Machine Learning, Neural Networks, Optimization, and CNNs. A survey class of neural network implementation and applications. Topics include: optimization - stochastic gradient descent, adaptive and 2nd order methods, normalization; convolutional neural networks - image processing, classification, detection, segmentation; recurrent neural networks - semantic understanding, translation, question-answering; cross-domain applications - image captioning, vision and language.   

CSE 490 G1 / 599 G1 Introduction to 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

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

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

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

CS 224V Conversational Virtual Assistants with Deep Learning Stanford University Fall 2022 This course focuses on the creation of effective, personalized, conversational assistants using large language neural models. It involves both theory and practical assignments, offering students a chance to design their own open-ended course project. Familiarity with NLP and task-oriented agents is beneficial. Computers will transform into effective, personalized, conversational assistants for everybody, including the pre-literate and the non-literate. Commercial chatbots today are notoriously brittle as they are hardcoded to handle a few possible choices of user inputs. Recently introduced large language neural models, such as GPT-3, are remarkably fluent, but they are often erroneous and prone to hallucinations. This course studies how we can tame these neural models into robust, trustworthy, and cost-effective conversational agents across all industries and languages.

Students will learn both the theory and practice with **two assignments**, and a **major open-ended course project** of their own design.

Topics include:

- Formal, executable meaning representation for conversational virtual assistants
- Contextual neural semantic parser for translating dialogues into a formal representation.
- Automatic generation of training data for dialogues from high-level schema and API specification with large language models.
- Using large language models in virtual assistants.
- Multilingual, mixed-initiative, multimodal assistants.
- Federated privacy-protecting assistants.   

CSE 490 G1 / 599 G1 Introduction to Deep Learning

Overview

Prerequisites

Learning objectives

Textbooks and other notes

Other courses in Deep Learning

CS 182/282A: Deep Neural Networks

CS 230 Deep Learning

CS 330 Deep Multi-Task and Meta Learning

CS 224V Conversational Virtual Assistants with Deep Learning

Courseware availability

Covered concepts