Deep Unsupervised Learning | UC Berkeley Spring 2024

google.com

Explore cutting-edge deep learning techniques in generative models and self-supervised learning. Taught by renowned instructors at UC Berkeley.

University CoursesDeep Learning

Introduction

This course will cover two areas of deep learning in which labeled data is not required: Deep Generative Models and Self-Supervised Learning. Recent advances in generative models have made it possible to realistically model high-dimensional raw data such as natural images, audio waveforms and text corpora. Strides in self-supervised learning have started to close the gap between supervised representation learning and unsupervised representation learning in terms of fine-tuning to unseen tasks.

screenshot

Highlights

  • Covers the theoretical foundations of deep generative models and self-supervised learning
  • Newly enabled applications of these cutting-edge deep learning techniques
  • Taught by a team of renowned instructors from UC Berkeley

Recommendation

This course is targeted towards a PhD level audience, but exceptional undergraduates could also be a good fit. It is a real course with substantial homework, a midterm, and a final project. Students interested in getting a head start can refer to the previous offering of the course.

How GetVM Works

Learn by Doing from Your Browser Sidebar

Access from Browser Sidebar

Access from Browser Sidebar

Simply install the browser extension and click to launch GetVM directly from your sidebar.

Select Your Playground

Select Your Playground

Choose your OS, IDE, or app from our playground library and launch it instantly.

Learn and Practice Side-by-Side

Learn and Practice Side-by-Side

Practice within the VM while following tutorials or videos side-by-side. Save your work with Pro for easy continuity.

Explore Similar Hands-on Tutorials

A Selective Overview of Deep Learning

3
Technical TutorialsDeep LearningMachine LearningNeural Networks
Comprehensive overview of key concepts and recent advancements in deep learning, covering neural network models, training techniques, and theoretical foundations.

Deep Multi-Task and Meta Learning | Comprehensive Guide

10
Video CoursesDeep LearningMachine Learning
In-depth understanding of state-of-the-art multi-task learning and meta-learning algorithms for few-shot learning, transfer learning, and lifelong learning.

Deep Learning Fundamentals | Neural Networks, Machine Learning

29
Video CoursesDeep LearningMachine Learning
Introductory book on deep learning fundamentals, covering neural networks, convolutional neural networks, recurrent nets, autoencoders, and deep learning use cases.

Machine Learning Specialization | AI, Machine Learning Fundamentals

10
Video CoursesData ScienceDeep LearningMachine Learning
Foundational online program on machine learning and AI applications, taught by Andrew Ng of DeepLearning.AI and Stanford Online.

Deep Learning for Natural Language Processing | University of Oxford

18
University CoursesDeep LearningMachine LearningNatural Language Processing
Dive into the latest advancements in deep learning for NLP, including text analysis, speech recognition, language translation, and more. Gain a solid theoretical foundation and practical experience.

Tensorflow for Deep Learning Research | Stanford University

18
University CoursesDeep LearningMachine LearningTensorFlow
Learn the fundamentals of TensorFlow for deep learning research. Build models for tasks like word embeddings, translation, and optical character recognition.

Introduction to Machine Learning | UC Berkeley CS 189 Course

14
University CoursesDeep LearningMachine Learning
Comprehensive machine learning course covering theoretical foundations, algorithms, and practical applications. Suitable for students with math and computer science background.

Deep Learning for Natural Language Processing | Stanford University

6
University CoursesDeep LearningMachine LearningNatural Language Processing
Dive deep into cutting-edge research in deep learning for natural language processing (NLP). Implement, train, and invent your own neural network models for a variety of NLP tasks.

Convolutional Neural Networks for Visual Recognition | Stanford University

12
University CoursesDeep LearningMachine Learning
Learn to implement, train and debug your own neural networks for computer vision and deep learning applications.