Colin Raffel | Applied Mathematics (APPM) Department Colloquium

preview_player
Показать описание
T5 and large language models; The good, the bad, and the ugly

  1. Maziar Raissi
Рекомендации по теме
Colin Raffel | 0:51:52

Colin Raffel | Applied Mathematics (APPM) Department Colloquium

Colin Raffel -- 0:26:46

Colin Raffel -- Explicit and Implicit Entropy Minimization in Proxy-Label-Based Semi-Supervised L...

Efficient Large-Scale AI 2:12:42

Efficient Large-Scale AI Workshop | Session 1: Skills acquisition and new capabilities

Should you switch 0:18:36

Should you switch from BERT to ALBERT?

2022.06 Large Language 1:07:25

2022.06 Large Language Models - Angeliki Lazaridou

Misha Belkin - 0:56:56

Misha Belkin - Emergence and grokking in 'simple' architectures - IPAM at UCLA

Partial Label Learning 0:07:04

Partial Label Learning by Entropy Minimization

Limits of Transfer 0:09:42

Limits of Transfer Learning (LOD 2020)

Scaling laws for 1:20:24

Scaling laws for large language models

Understanding BERT: The 0:11:01

Understanding BERT: The Transformer in the Encoder (with Mohit Iyyer)

T5 | Lecture 0:15:20

T5 | Lecture 55 (Part 2) | Applied Deep Learning (Supplementary)

Leaking training data 0:09:34

Leaking training data from GPT-2. How is this possible?

Emtiyaz Khan - 0:52:06

Emtiyaz Khan - The Bayesian Learning Rule for Adaptive AI

Lightning talks: Skills 0:47:26

Lightning talks: Skills acquisition and new capabilities

Neural Networks Architecture 0:52:54

Neural Networks Architecture Seminar. Lecture 6: Transformer Networks

Exploring the Limits 1:40:09

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

Deep Attention Mechanism 1:18:50

Deep Attention Mechanism for Multimodal Intelligence: Perception, Reasoning, & Expression

Neural data-to-text generation: 0:16:54

Neural data-to-text generation: A comparison between pipeline and end-to-end architectures

Precision Health: Imagine 0:57:48

Precision Health: Imagine What Can We Do, Computationally

Scaling Law with 0:25:42

Scaling Law with Learning Rate Annealing - ArXiv:2408.11029

Transformer XL | 1:31:02

Transformer XL | AISC Trending Papers

Applying BERT to 0:21:13

Applying BERT to Question Answering (SQuAD v1.1)

Towards Improved Transfer 0:44:15

Towards Improved Transfer Learning with Hugo Larochelle - 631