About the station

When you build a model for natural language processing (NLP), such as a recurrent neural network, it helps a ton if you’re not starting from zero. In other words, if you can draw upon other datasets for building your understanding of word meanings, and then use your training dataset just for subject-specific refinements, you’ll get farther than just using your training dataset for everything. This idea of starting with some pre-trained resources has an analogue in computer vision, where initializations from ImageNet used for the first few layers of a CNN have become the new standard. There’s a similar progression under way in NLP, where simple(r) embeddings like word2vec are giving way to more advanced pre-processing methods that aim to capture more sophisticated understanding of word meanings, contexts, language structure, and more. Relevant links: https://thegradient.pub/nlp-imagenet/

Homepage

http://lineardigressions.com/

Give them some love

Latest bursts

So long, and thanks for all the fish

So long, and thanks for all the fish

So long, and thanks for all the fish

Aired 1 year ago

A Reality Check on AI-Driven Medical Assistants

A Reality Check on AI-Driven Medical Assistants

A Reality Check on AI-Driven Medical Assistants

Aired 1 year ago

A Data Science Take on Open Policing Data

A Data Science Take on Open Policing Data

A Data Science Take on Open Policing Data

Aired 1 year ago

Procella: YouTube's super-system for analytics data storage

Procella: YouTube's super-system for analytics data storage

Procella: YouTube's super-system for analytics data storage

Aired 1 year ago

Procella: YouTube's super-system for analytics data storage

Procella: YouTube's super-system for analytics data storage

Procella: YouTube's super-system for analytics data storage

Aired 1 year ago

The Data Science Open Source Ecosystem

The Data Science Open Source Ecosystem

The Data Science Open Source Ecosystem

Aired 1 year ago

Rock the ROC Curve

Rock the ROC Curve

Rock the ROC Curve

Aired 1 year ago

Criminology and Data Science

Criminology and Data Science

Criminology and Data Science

Aired 1 year ago

Racism, the criminal justice system, and data science

Racism, the criminal justice system, and data science

Racism, the criminal justice system, and data science

Aired 1 year ago

Racism, the criminal justice system, and data science

Racism, the criminal justice system, and data science

Racism, the criminal justice system, and data science

Aired 1 year ago

An interstitial word from Ben

An interstitial word from Ben

An interstitial word from Ben

Aired 1 year ago

Convolutional Neural Networks

Convolutional Neural Networks

Convolutional Neural Networks

Aired 1 year ago

Convolutional Neural Networks

Convolutional Neural Networks

Convolutional Neural Networks

Aired 1 year ago

Stein's Paradox

Stein's Paradox

Stein's Paradox

Aired 1 year ago

Protecting Individual-Level Census Data with Differential Privacy

Protecting Individual-Level Census Data with Differential Privacy

Protecting Individual-Level Census Data with Differential Privacy

Aired 1 year ago

Causal Trees

Causal Trees

Causal Trees

Aired 1 year ago

The Grammar Of Graphics

The Grammar Of Graphics

The Grammar Of Graphics

Aired 1 year ago

The Grammar Of Graphics

The Grammar Of Graphics

The Grammar Of Graphics

Aired 1 year ago

Gaussian Processes

Gaussian Processes

Gaussian Processes

Aired 1 year ago

Keeping ourselves honest when we work with observational healthcare data

Keeping ourselves honest when we work with observational healthcare data

Keeping ourselves honest when we work with observational healthcare data

Aired 1 year ago

Changing our formulation of AI to avoid runaway risks: Interview with Prof. Stuart Russell

Changing our formulation of AI to avoid runaway risks: Interview with Prof. Stuart Russell

Changing our formulation of AI to avoid runaway risks: Interview with Prof. Stuart Russell

Aired 1 year ago

Putting machine learning into a database

Putting machine learning into a database

Putting machine learning into a database

Aired 1 year ago

Understanding Covid-19 transmission: what the data suggests about how the disease spreads

Understanding Covid-19 transmission: what the data suggests about how the disease spreads

Understanding Covid-19 transmission: what the data suggests about how the disease spreads

Aired 1 year ago

Understanding Covid-19 transmission: what the data suggests about how the disease spreads

Understanding Covid-19 transmission: what the data suggests about how the disease spreads

Understanding Covid-19 transmission: what the data suggests about how the disease spreads

Aired 1 year ago

Network effects re-release: when the power of a public health measure lies in widespread adoption

Network effects re-release: when the power of a public health measure lies in widespread adoption

Network effects re-release: when the power of a public health measure lies in widespread adoption

Aired 1 year ago