1658983917_maxresdefault.jpg
36
10:09

DeepMind Makes Prototyping Papers Easy with ACME

DeepMind’s ACME framework makes implementing deep reinforcement learning agents incredibly easy. By using a modularized approach to agent design, agents can be scaled from a single thread up to hundreds easily. In this video I’ll give you a brief overview of how all the pieces fit together. Learn how to turn deep reinforcement learning papers […]
1657668526_maxresdefault.jpg
38
06:46

Hugging Face Data Sets (11.3)

Hugging Face hub provides datasets that can be downloaded by Python programs and used to fine tune or train existing transformers and other neural networks for natural language processing (NLP). This video demonstrates how to make use of Hugging Face datasets in Python. Code for This Video: https://github.com/jeffheaton/t81_558_deep_learning/blob/master/t81_558_class_11_03_hf_datasets.ipynb Course Homepage: https://sites.wustl.edu/jeffheaton/t81-558/ Follow Me/Subscribe: https://www.youtube.com/user/HeatonResearch https://github.com/jeffheaton […]
1656459240_maxresdefault.jpg
114
08:09

What have AI language models learned?

AI and ML researchers developed Large Language Models (LLMs) like BERT to help machines interact with natural language, improving their abilities in tasks like chat and translation! Nithum Thain, Senior Software Engineer at Google PAIR, highlights the Explorable “What Have Language Models Learned” by Adam Pearce and shares what we can learn about BERT by […]
1655332846_maxresdefault.jpg
45
10:49

Introduction to Hugging Face Classifiers (11.1)

Hugging Face provides a hub where you can select select pretrained transformers and data sets for natural language processing (NLP). This video introduces Hugging Face and shows how it can be used for translation, named-entity extraction, text generation, and other NLP tasks. Code for This Video: https://github.com/jeffheaton/t81_558_deep_learning/blob/master/t81_558_class_11_01_huggingface.ipynb Course Homepage: https://sites.wustl.edu/jeffheaton/t81-558/ Follow Me/Subscribe: https://www.youtube.com/user/HeatonResearch https://github.com/jeffheaton Tweets […]
1654125710_maxresdefault.jpg
11
52:11

Hedvig Kjellström: Learning compositional, structured, and interpretable models of the world

Hedvig Kjellström is a professor in the Division of Robotics, Perception and Learning, Department of Intelligent Systems at KTH Royal Institute of Technology, Sweden, and Principal AI Scientist at Silo AI, Sweden. This talk was part of the colloquium of the Cluster of Excellence “Machine Learning: New Perspectives for Science”. Abstract: Despite their fantastic achievements […]
1653776072_maxresdefault.jpg
119
04:01

Applications of Deep Neural Networks for Keras – Paperback, Kindle & Free PDF

This book contains a complete course on deep neural work applications with Keras. I provide YouTube videos and a GitHub repository of all code and text for this book. Topics covered include tabular data, images, GANs, reinforcement learning, transformers, and natural language processing. All examples are in the Python programming language. Link to buy the […]
1652906056_maxresdefault.jpg
9
01:18

SingularityNET: Semantic Search and Processing for text, image and video

An Open Source, interpretable, semantic search solution for unstructured data including text, image, and video files. The solution features an NLP transformer network for semantic search of text documents and a computer vision model that allows for cross-modal semantic search in images. https://proposals.deepfunding.ai/collaborate/edb5d68d-6c92-4e16-80ca-f50ed07888b2 —- SingularityNET is a decentralized marketplace for artificial intelligence. We aim to […]
1650923178_maxresdefault.jpg
3
52:45

Mixture-of-Experts and Trends in Large-Scale Language Modeling with Irwan Bello – #569

Today we’re joined by Irwan Bello, formerly a research scientist at Google Brain, and now on the founding team at a stealth AI startup. We begin our conversation with an exploration of Irwan’s recent paper, Designing Effective Sparse Expert Models, which acts as a design guide for building sparse large language model architectures. We discuss […]
1649969827_maxresdefault.jpg
15
08:06

Keras Transfer Learning for NLP (9.3)

Natural language processing typically makes use of embeddings, which are previously trained neural networks. This video introduces transfer learning for natural language processing in Keras. Code for This Video: https://github.com/jeffheaton/t81_558_deep_learning/blob/master/t81_558_class_09_3_transfer_nlp.ipynb Course Homepage: https://sites.wustl.edu/jeffheaton/t81-558/ Follow Me/Subscribe: https://www.youtube.com/user/HeatonResearch https://github.com/jeffheaton Tweets by jeffheaton Support Me on Patreon: https://www.patreon.com/jeffheaton Source of this machine learning/AI Video
1649634865_maxresdefault.jpg
189
09:31

Google's New AI can do Anything (PaLM AI)

The first 1,000 people to use the link or my code “ainews” will get a 1 month free trial of Skillshare: https://skl.sh/ainews04221 Google has been working on its relatively secret Pathways AI project for almost a year now, and now they’ve shown its first results in the form of PaLM AI, which is the biggest […]
1649464223_maxresdefault.jpg
73
55:54

#73 – YASAMAN RAZEGHI & Prof. SAMEER SINGH – NLP benchmarks [UNPLUGGED]

Patreon: https://www.patreon.com/mlst Discord: https://discord.gg/ESrGqhf5CB Pod version: https://anchor.fm/machinelearningstreettalk/episodes/73—YASAMAN-RAZEGHI–Prof–SAMEER-SINGH—NLP-benchmarks-e1grvjj This week we speak with Yasaman Razeghi and Prof. Sameer Singh from UC Urvine. Yasaman recently published a paper called Impact of Pretraining Term Frequencies on Few-Shot Reasoning where she demonstrated comprehensively that large language models only perform well on reasoning tasks because they memorise the dataset. For […]
1648014586_maxresdefault.jpg
9
52:12

Big Science and Embodied Learning at Hugging Face 🤗 with Thomas Wolf – #564

Today we’re joined by Thomas Wolf, co-founder and chief science officer at Hugging Face 🤗. We cover a ton of ground In our conversation, starting with Thomas’ interesting backstory as a quantum physicist and patent lawyer, and how that lead him to a career in machine learning. We explore how Hugging Face began, what the […]
1647724403_maxresdefault.jpg
32
05:23

Have high gpu prices got you down?

GTC 2022 is almost upon us. That means it’s time for a giveaway. All you have to do is subscribe to the channel, watch the keynote, take a screenshot of yourself in the keynote session and email it to phil@neuralnet.ai. The keynote speech is March 22 at 8 AM PST. GPU giveaway is restricted to […]
1647332174_maxresdefault.jpg
26
13:27

How I learned to stop worrying and love Artificial Super Intelligence

I think fears of artiicial super intelligence (in pop culture, specifically) are a bit overblown. I lay out my case in this vodeo. Learn how to turn deep reinforcement learning papers into code: Get instant access to all my courses, including the new Hindsight Experience Replay course, with my subscription service. $24.99 a month gives […]
1646253213_maxresdefault.jpg
3
49:54

Rob Munro Interview – Human-in-the-Loop AI for Emergency Response & More

In this episode, I chat with Rob Munro, CTO of the newly branded Figure Eight, formerly known as CrowdFlower. Figure Eight’s Human-in-the-Loop AI platform supports data science & machine learning teams working on autonomous vehicles, consumer product identification, natural language processing, search relevance, intelligent chatbots, and more. Rob and I had a really interesting discussion […]
1645601771_maxresdefault.jpg
7
01:22:15

Trends in Deep Reinforcement Learning with Kamyar Azizzadenesheli – #560

Today we’re joined by Kamyar Azizzadenesheli, an assistant professor at Purdue University, to close out our AI Rewind 2021 series! In this conversation, we focused on all things deep reinforcement learning, starting with a general overview of the direction of the field, and though it might seem to be slowing, thats just a product of […]
1645229392_maxresdefault.jpg
53
19:29

Mastering Robotics with Hindsight Experience Replay | Paper Analysis

Hindisght experience replay works pretty simply: swap out the original goal your agent was trying to receive with one it actually received. It deals with environments with sparse rewards and large state spaces. Check out my analysis of the paper here. Learn how to turn deep reinforcement learning papers into code: Get instant access to […]
1645207758_maxresdefault.jpg
122
10:28

Why I'm Not Putting My New Course On Udemy

Learn how to turn deep reinforcement learning papers into code: Get instant access to all my courses, including the new Hindsight Experience Replay course, with my subscription service. $24.99 a month gives you instant access to 24 hours of instructional content plus access to future updates, added monthly. Discounts available for Udemy students (enrolled longer […]
1642844416_maxresdefault.jpg
8
02:36

SingularityNET: Catalyst Fund7 Proposal | NLP Applied to Conflict Resolution

NLP Applied to Conflict Resolution, Catalyst Fund7 Proposal – Problem Statement: Dispute resolution generally happens behind closed doors with no public insight into determining what is likely to support a good outcome. Solution: Developing ML NLP models to support better outcomes in conflict resolution. Cardano Full Proposal: https://cardano.ideascale.com/a/dtd/NLP-Applied-to-Conflict-Resolution/383548-48088 Additional Information: https://www.youtube.com/channel/UCvehpWzBd0nD47q9EGAg-sA 🦾SNET Blog: https://blog.singularitynet.io/singularitynet-cardano-fund7-challenge-proposal-concept-videos-4bec9baa7f35 —- […]
1642480134_maxresdefault.jpg
92
15:09

Applications of Deep Neural Networks Course Overview (1.1, Spring 2022)

Spring 2022 Version. Applications of deep neural networks is a course offered in a hybrid format by Washington University in St. Louis. This course introduces Keras deep neural networks and highlights applications that neural networks are particularly adept at handling compared to previous machine learning models. Deep learning is a group of exciting new technologies […]
1642059668_maxresdefault.jpg
29
29:08

Proximal Policy Optimization is Easy with Tensorflow 2 | PPO Tutorial

Proximal Policy Optimization (PPO) has emerged as a powerful on policy actor critic algorithm. You might think that implementing it is difficult, but in fact tensorflow 2 makes coding up a PPO agent relatively simple. We’re going to take advantage of my PyTorch code for this, as it serves as a great basis to expand […]
1641663298_maxresdefault.jpg
9
01:23:09

Trends in NLP with John Bohannon – #550

Today we’re joined by friend of the show John Bohannon, the director of science at Primer AI, to help us showcase all of the great achievements and accomplishments in NLP in 2021! In our conversation, John shares his two major takeaways from last year, 1) NLP as we know it has changed, and we’re back […]
1641408884_maxresdefault.jpg
13
14:54

Basic Hyperparameter Tuning in DeepMinds ACME Framework

In today’s ACME deep reinforcement learning framework tutorial, I will showy ou how to do some basic hyperparameter tuning in their built in Deep Q Learning agent. Learn how to turn deep reinforcement learning papers into code: Deep Q Learning: https://www.udemy.com/course/deep-q-learning-from-paper-to-code/?couponCode=DQN-AUG-2021 Actor Critic Methods: https://www.udemy.com/course/actor-critic-methods-from-paper-to-code-with-pytorch/?couponCode=AC-AUG-2021 Natural Language Processing from First Principles: https://www.udemy.com/course/natural-language-processing-from-first-principles/?couponCode=NLP1-AUG-2021 Reinforcement Learning Fundamentals […]