Published Oct 23, 2019

Reproducing Deep Learning Models

Kyle Polich hosts Rajiv Shah as he critiques and attempts to reproduce a deep learning model for earthquake prediction, revealing challenges like data leakage and underscoring the need for baseline models, transparency, and robust validation techniques in model building.

Episode Highlights

Topics covered

Popular Clips

Episode Highlights

Related Episodes

Earthquake Detection with Crowd-sourced Data
Answers 383 questions
ML Ops Best Practices
Answers 383 questions
Easily Fooling Deep Neural Networks
Answers 383 questions
Deep Learning for Road Traffic Forecasting
Answers 383 questions
Drug Discovery with Machine Learning
Answers 383 questions
Machine Learning Done Wrong
Answers 383 questions
ELMo
Answers 383 questions
Deep Fakes
Answers 383 questions
[MINI] Primer on Deep Learning
Answers 383 questions
Do We Need Deep Learning in Time Series
Answers 383 questions
Explainable Climate Science
Answers 383 questions
Transfer Learning
Answers 383 questions
Stealing Models from the Cloud
Answers 383 questions
Applied Data Science in Industry
Answers 383 questions
ML Ops
Answers 383 questions

Dexa/Kyle Polich

Reproducing Deep Learning Models

Topics covered

Popular Clips

Reproducibility in Machine Learning

Model Building Wisdom

Earthquake Aftershock Prediction

Machine Learning Best Practices

Avoiding Data Leakage

Deep Learning in Earthquakes

Model Performance Analysis

Data Science Bootcamp

Episode Highlights

Deep Learning Critique

Model Reproducibility

Model Evaluation Techniques

Related Episodes

Earthquake Detection with Crowd-sourced Data

ML Ops Best Practices

Easily Fooling Deep Neural Networks

Deep Learning for Road Traffic Forecasting

Drug Discovery with Machine Learning

Machine Learning Done Wrong

ELMo

Deep Fakes

[MINI] Primer on Deep Learning

Do We Need Deep Learning in Time Series

Explainable Climate Science

Transfer Learning

Stealing Models from the Cloud

Applied Data Science in Industry

ML Ops

Reproducing Deep Learning Models

Topics covered

Popular Clips

Episode Highlights

Deep Learning CritiqueRajiv Shah critiques a deep learning model for earthquake prediction, highlighting the lack of a baseline model and the trade-off between interpretability and accuracy. His analysis underscores the importance of foundational steps and transparency in model building.

Deep Learning Critique

Model ReproducibilityRajiv Shah's attempt to reproduce an earthquake-predicting deep learning model revealed significant challenges and insights. His work underscores the importance of open science and collaboration in improving model reliability and academic discourse.

Model Reproducibility

Model Evaluation TechniquesRajiv Shah uncovers critical issues in reproducing a deep learning model for earthquake prediction, focusing on data leakage and performance metrics. His analysis reveals the importance of robust validation techniques to ensure model reliability.

Model Evaluation Techniques

Related Episodes