Tanmay Bakshi
Ranking Amazon Reviews by Quality with Pointwise Ratings learned from Pairwise Data
#1about 7 minutes
Ranking Amazon reviews by learning a quality score
The model learns to assign a continuous quality score to reviews by training on a classification task rather than a direct regression problem.
#2about 7 minutes
How neural networks learn through feature embeddings
Neural networks transform complex input data into a high-dimensional embedding space where it becomes linearly separable for classification.
#3about 6 minutes
Processing sequential text data with Word2Vec and RNNs
Word2Vec creates semantic vector representations of words, which are then processed sequentially by Recurrent Neural Networks (RNNs) to understand context.
#4about 5 minutes
Identifying the limitations of recurrent neural networks
Recurrent neural networks are slow due to their sequential nature, lack general-purpose understanding, and struggle to process bidirectional context simultaneously.
#5about 8 minutes
Introducing the BERT and transformer architecture
The Transformer architecture uses self-attention to process text in parallel, enabling BERT to learn general, contextual word representations through masked language modeling.
#6about 6 minutes
Demonstrating self-attention with a character-level model
A simplified character-level model called 'Artist BERT' demonstrates how self-attention works by predicting masked characters in artist names.
#7about 8 minutes
Training a pointwise ranker from pairwise review data
A Siamese network architecture processes pairs of reviews to determine which is better, implicitly learning a pointwise quality score for each individual review.
Related jobs
Jobs that call for the skills explored in this talk.
Matching moments
07:44 MIN
Training a model to rank reviews with relative values
TEST
Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Upgrade to PRO for unlimited access to the full archive.
You have an account? Log in
07:29 MIN
Quantifying the usefulness of an Amazon review
TEST
Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Upgrade to PRO for unlimited access to the full archive.
You have an account? Log in
06:50 MIN
Showcasing real-time AI application examples
Convert batch code into streaming with Python
Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Upgrade to PRO for unlimited access to the full archive.
You have an account? Log in
08:11 MIN
Q&A on data, learning resources, and algorithms
Machine Learning in ML.NET
Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Upgrade to PRO for unlimited access to the full archive.
You have an account? Log in
03:38 MIN
How neural networks and quality data power AI translation
Fireside Chat: Deep Learning, Deep Impact: Harnessing AI for Language Innovation
Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Upgrade to PRO for unlimited access to the full archive.
You have an account? Log in
01:54 MIN
Exploring diverse ML workloads with Transformers.js
Prompt API & WebNN: The AI Revolution Right in Your Browser
Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Upgrade to PRO for unlimited access to the full archive.
You have an account? Log in
03:31 MIN
Q&A on machine learning and qubit interaction
Schroedinger's cat: Thinking in- and outside the box of quantum mechanics
Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Upgrade to PRO for unlimited access to the full archive.
You have an account? Log in
02:27 MIN
An overview of an AI-powered code reviewer
How we built an AI-powered code reviewer in 80 hours
Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Upgrade to PRO for unlimited access to the full archive.
You have an account? Log in
Featured Partners
Related Videos
What do language models really learn
Tanmay Bakshi
TEST
WAD
Mastering Image Classification: A Journey with Cakes
Carly Richmonds
Machine learning in the browser with TensorFlowjs
Håkan Silfvernagel
A beginner’s guide to modern natural language processing
Jodie Burchell
WeAreDevelopers LIVE - Vector Similarity Search Patterns for Efficiency and more
Chris Heilmann, Daniel Cranney, Raphael De Lio & Developer Advocate at Redis
Building Products in the era of GenAI
Julian Joseph
Develop AI-powered Applications with OpenAI Embeddings and Azure Search
Rainer Stropek
Related Articles
View all articles


.png?w=240&auto=compress,format)
From learning to earning
Jobs that call for the skills explored in this talk.

Warmwind
€120K
PyTorch
Tensorflow
Machine Learning


Warmwind
€240K
Senior
PyTorch
Tensorflow
Machine Learning


Squarepoint Capital
London, United Kingdom
Intermediate
gRPC
Linux
Kotlin
PyTorch
PostgreSQL
+3

Devoteam
Intermediate
PyTorch
PySpark
Tensorflow
Adobe InDesign
Machine Learning


