WAD
TEST
#1about 7 minutes
Quantifying the usefulness of an Amazon review
A neural network ranks Amazon reviews by assigning a continuous scalar value that represents helpfulness, trained on user feedback data.
#2about 6 minutes
How neural networks learn features in embedding spaces
Deep neural networks project input data into an embedding space where it becomes linearly separable for a final classifier.
#3about 10 minutes
The evolution and limitations of traditional NLP models
Techniques like Word2Vec create semantic vectors for words, but recurrent neural networks (RNNs) that use them are slow, non-parallelizable, and domain-specific.
#4about 8 minutes
How BERT and transformers solve core NLP challenges
The BERT model, built on the transformer architecture, is domain-independent, parallelizable, and understands word context by using a masked language modeling training approach.
#5about 7 minutes
Building a character-level model with self-attention
A custom 'Artist BERT' model demonstrates how self-attention layers can predict masked characters in a sequence by understanding positional and contextual information.
#6about 8 minutes
Training a model to rank reviews with relative values
The review ranker is trained as a classification problem on pairs of reviews, forcing it to learn a scalar helpfulness value without being given absolute scores.
Related jobs
Jobs that call for the skills explored in this talk.
Matching moments
06:40 MIN
Ranking Amazon reviews by learning a quality score
Ranking Amazon Reviews by Quality with Pointwise Ratings learned from Pairwise Data
08:25 MIN
From Word2Vec and LSTMs to modern transformers
What do language models really learn
07:44 MIN
Training a pointwise ranker from pairwise review data
Ranking Amazon Reviews by Quality with Pointwise Ratings learned from Pairwise Data
02:59 MIN
Highlighting successful applications of deep learning
The pitfalls of Deep Learning - When Neural Networks are not the solution
01:54 MIN
Exploring diverse ML workloads with Transformers.js
Prompt API & WebNN: The AI Revolution Right in Your Browser
05:33 MIN
Using evaluators to compare AI model variants
Bringing AI Model Testing and Prompt Management to Your Codebase with GitHub Models
08:06 MIN
Introducing the BERT and transformer architecture
Ranking Amazon Reviews by Quality with Pointwise Ratings learned from Pairwise Data
02:52 MIN
The role of transformers and the attention mechanism
AI'll Be Back: Generative AI in Image, Video, and Audio Production
Featured Partners
Related Videos
47:26Ranking Amazon Reviews by Quality with Pointwise Ratings learned from Pairwise Data
Tanmay Bakshi
21:01Hybrid AI: Next Generation Natural Language Processing
Jan Schweiger
27:23How We Built a Machine Learning-Based Recommendation System (And Survived to Tell the Tale)
Dora Petrella
26:54Make it simple, using generative AI to accelerate learning
Duan Lightfoot
28:07How we built an AI-powered code reviewer in 80 hours
Yan Cui
22:07WWC24 - Ankit Patel - Unlocking the Future Breakthrough Application Performance and Capabilities with NVIDIA
Ankit Patel
26:30Three years of putting LLMs into Software - Lessons learned
Simon A.T. Jiménez
22:11How computers learn to see – Applying AI to industry
Antonia Hahn
Related Articles
View all articles
From learning to earning
Jobs that call for the skills explored in this talk.
Infosupport
Veenendaal, Netherlands
€0K
Natural Language Processing
Understanding Recruitment Group
Barcelona, Spain
Remote
Node.js
Computer Vision
Machine Learning
NLP People
Municipality of Valencia, Spain
Intermediate
GIT
Linux
NoSQL
NumPy
Keras
+11