Page 7 of 13 for All Posts - Page 7

Inside Chirpy Cardinal: Stanford's Open-Source Social Chatbot that Won 2nd place in the Alexa Prize

Last year, Stanford won 2nd place in the Alexa Prize Socialbot Grand Challenge for social chatbots. In this post, we look into building a chatbot that combines the flexibility and naturalness of neural dialog generation with the reliability and practicality of scripted dialogue.

Neural Mechanics: Symmetry and Broken Conservation Laws In Deep Learning Dynamics

Daniel Kunin and Hidenori Tanaka

By exploiting architectural symmetry, our work demonstrates that we can analytically describe the learning dynamics of various parameter combinations at finite learning rates and batch sizes for state of the art architectures trained on any dataset.

Do Language Models Know How Heavy an Elephant Is?

Xikun Zhang

Humans have a pretty good sense of scale, like the weight or price of different objects, but do pre-trained language representations? We measure how well pre-trained text representations capture scale and also come up with a improved version of BERT that captures scale better.

Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately

Fereshte Khani

Machine learning models rely on some spurious features that we humans know to avoid. A natural remedy is to remove such features from the data. However, in this work we show that removal of spurious features can decrease accuracy due to the inductive biases of overparameterized models.

Blue People v. City of Ney

Fereshte Khani

Discriminatory behavior towards certain groups by machine learning (ML) models is concerning in critical applications such as hiring. We show that when ML models use noisy features, they're incentivized to devalue a good score when the candidate is from a lower-performing group.

A Model-Based Approach Towards Identifying the Brain's Learning Algorithms

Aran Nayebi

A major long-term goal of computational neuroscience is to identify the brain's learning algorithms. Can we use artificial neural networks to guide this discovery?

iGibson: A Simulation Environment to Train AI Agents in Large Realistic Scenes

Roberto Martín-Martín

Introducing iGibson, an open source, fully academically developed simulation environment for interactive tasks in large realistic scenes.

Stanford AI Lab Papers and Talks at NeurIPS 2020

Compiled by Megha Srivastava

All the great work from the Stanford AI Lab accepted at NeurIPS 2020, all in one place.

Learning from Language Explanations

Jesse Mu and Shikhar Murty

Language is a crucial way for humans to teach other humans. Can we use language to teach machines?

Stanford AI Lab Papers and Talks at CoRL 2020

Compiled by Annie Xie

All the great work from the Stanford AI Lab accepted at CoRL 2020, all in one place.