Published Jan 26, 2020

Interpretable One Shot Learning

Delve into the future of NLP interpretability with Su Wang and Kyle Polich as they explore semantic spaces, Bayesian methods, and joint distribution models to unlock cognitive mapping and one shot learning, innovating language processing with minimal data.

Episode Highlights

Topics covered

Episode Highlights

Related Episodes

[MINI] Natural Language Processing
Answers 383 questions
[MINI] One Shot Learning
Answers 383 questions
Transfer Learning
Answers 383 questions
Visualization and Interpretability
Answers 383 questions
Named Entity Recognition
Answers 383 questions
Interpretability Practitioners
Answers 383 questions
Interpretability
Answers 383 questions
Understanding Neural Networks
Answers 383 questions
Interpretability Tooling
Answers 383 questions
Let's Talk About Natural Language Processing
Answers 383 questions
Analysis of Unstructured Data
Answers 383 questions
Interpretable AI in Healthcare
Answers 383 questions
Trusting Machine Learning Models with LIME
Answers 383 questions
Serverless NLP Model Training
Answers 383 questions
ELMo
Answers 383 questions

Dexa/Kyle Polich

Interpretable One Shot Learning

Topics covered

Popular Clips

Interpretable Word Learning

Training Data Sets

Modeling Concepts and Properties

Bayesian Approaches, Distributional Structure

Exploring Data Skepticism

Cognitive Connections

One Shot Learning

Modeling Concepts, Properties, and Context

Semantic Space Exploration

Learning from Text and Narrative Coherence

Inference and Semantic Space

Episode Highlights

Interpretability in NLP

Modeling Concepts

One Shot Learning

Related Episodes

[MINI] Natural Language Processing

[MINI] One Shot Learning

Transfer Learning

Visualization and Interpretability

Named Entity Recognition

Interpretability Practitioners

Interpretability

Understanding Neural Networks

Interpretability Tooling

Let's Talk About Natural Language Processing

Analysis of Unstructured Data

Interpretable AI in Healthcare

Trusting Machine Learning Models with LIME

Serverless NLP Model Training

ELMo

Interpretable One Shot Learning

Topics covered

Popular Clips

Episode Highlights

Interpretability in NLPSu Wang joins Kyle Polich on the Data Skeptic to discuss the challenges and innovations in making NLP models more interpretable. They explore the use of semantic spaces and Bayesian techniques to improve understanding and representation of language.

Interpretability in NLP

Modeling Concepts

One Shot LearningSu Wang explores the intriguing concept of one shot learning, where minimal data is used to infer the properties of new words. This method promises significant advancements in language processing and cognitive semantics.

One Shot Learning

Related Episodes