Discovering Symbolic Inductive Biases | AISC

Channel:
Canada LLMs Explained - Aggregate Intellect - AI.SCIENCE
Subscribers:
22,300
Published on ● Video Link: https://www.youtube.com/watch?v=NllV-2PZI0k


Duration: 39:49
332 views
10

Speaker(s): Miles Cranmer
Facilitator(s):

Find the recording, slides, and more info at https://ai.science/e/discovering-symbolic-inductive-biases--W2vGc7YnT6NdR5Oso68F

Motivation / Abstract
The authors present an approach offer alternative directions for interpreting neural networks and discovering novel physical principles from the representations they learn. This is accomplished by applying symbolic regression to components of the learned model to extract explicit physical relations. This is also applied to a non-trivial cosmology example—a detailed dark matter simulation—and discover a new analytic formula which can predict the concentration of dark matter from the mass distribution of nearby cosmic structures.

What was discussed?
- What is symbolic regression?
- What does it mean for a DL model to have a separable internal structure?
- How do you deal with the curse of dimensionality?

------
#AISC hosts 3-5 live sessions like this on various AI research, engineering, and product topics every week! Visit https://ai.science for more details



Other Videos By LLMs Explained - Aggregate Intellect - AI.SCIENCE


2020-09-01DeepFakes & Explainable AI Applications in NLP, Biomedical & Malware Classification
2020-08-28AI Ethics Then & Now: A Look Back on the Last Five Years | AISC
2020-08-27Beyond Accuracy: Behavioral Testing of NLP Models with CheckList | AISC
2020-08-27The Summary Loop: Learning to Write Abstractive Summaries Without Examples + Demo | AISC
2020-08-26[MEM] Learning Permutation Invariant Representations using Memory Networks | AISC
2020-08-26AI for Fun!
2020-08-25[T-Fixup] Improving Transformer Optimization Through Better Initialization | AISC
2020-08-25A review of ML for aerospace systems health management | AISC
2020-08-21An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph | AISC
2020-08-20Overview of Synthetic Data and Simulations | AISC
2020-08-19Discovering Symbolic Inductive Biases | AISC
2020-08-19Product Ideation - Art of Finding the Right Problem to Work on! | AISC
2020-08-19Pink Diamond - Data Driven Prediction of Venture Success | Workshop Capstone
2020-08-19Review Nuggets - Mining Insight from Consumer Product Reviews | Workshop Capstone
2020-08-19Fast Film - Emotionally Aware Movie Recommender | Workshop Capstone
2020-08-19Acetock - Stock Prediction Tool for Amateur Investors | Workshop Capstone
2020-08-19Saramsh - Patent Document Summarization using BART | Workshop Capstone
2020-08-19MindfulZen - Data Driven Stress Buster | Workshop Capstone
2020-08-14Machine Learning and the Earth: Applying AI to address some of the world’s greatest challenges
2020-08-13Xun Wang (GEICO): 7 Job Profiles to Demystify the Data Science Career Landscape
2020-08-12Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning | AISC