Flexible Neural Representation for Physics Prediction | AISC Trending Paper

Channel:
Canada LLMs Explained - Aggregate Intellect - AI.SCIENCE
Subscribers:
22,300
Published on ● Video Link: https://www.youtube.com/watch?v=Q0hjK61uO_8


Duration: 1:18:42
756 views
8

Toronto Deep Learning Series, 16 July 2018

For slides & more information, visit https://tdls.a-i.science/events/2018-07-16/

Paper Review: https://arxiv.org/abs/1806.08047

Speaker: https://www.linkedin.com/in/bebart-janbek-3a834154/
Organizer: https://www.linkedin.com/in/amirfz/

Host: http://www.loblawdigital.ca/

Paper abstract:
"Humans have a remarkable capacity to understand the physical dynamics of objects in their environment, flexibly capturing complex structures and interactions at multiple levels of detail. Inspired by this ability, we propose a hierarchical particle-based object representation that covers a wide variety of types of three-dimensional objects, including both arbitrary rigid geometrical shapes and deformable materials. We then describe the Hierarchical Relation Network (HRN), an end-to-end differentiable neural network based on hierarchical graph convolution, that learns to predict physical dynamics in this representation. Compared to other neural network baselines, the HRN accurately handles complex collisions and nonrigid deformations, generating plausible dynamics predictions at long time scales in novel settings, and scaling to large scene configurations. These results demonstrate an architecture with the potential to form the basis of next-generation physics predictors for use in computer vision, robotics, and quantitative cognitive science."



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


2018-09-19Reconstructing quantum states with generative models | TDLS Author Speaking
2018-09-13All-optical machine learning using diffractive deep neural networks | TDLS
2018-09-05Recurrent Models of Visual Attention | TDLS
2018-08-28Eve: A Gradient Based Optimization Method with Locally and Globally Adaptive Learning Rates | TDLS
2018-08-20TDLS: Large-Scale Unsupervised Deep Representation Learning for Brain Structure
2018-08-14Principles of Riemannian Geometry in Neural Networks | TDLS
2018-08-07Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond | TDLS
2018-07-30Program Language Translation Using a Grammar-Driven Tree-to-Tree Model | TDLS
2018-07-23Explainable Neural Networks based on Additive Index Models | TDLS
2018-07-18TMLS2018 - Machine Learning in Production, Panel Discussion
2018-07-16Flexible Neural Representation for Physics Prediction | AISC Trending Paper
2018-07-10Connectionist Temporal Classification, Labelling Unsegmented Sequence Data with RNN | TDLS
2018-06-25Learning to Represent Programs with Graphs | TDLS
2018-06-19Quantum generative adversarial networks | TDLS Author Speaking
2018-06-12[SAGAN] Self-Attention Generative Adversarial Networks | TDLS
2018-06-05[ELMo] Deep Contextualized Word Representations | AISC
2018-05-23Few-Shot Learning Through an Information Retrieval Lens | TDLS
2018-05-14Improving Supervised Bilingual Mapping of Word Embeddings | TDLS
2018-05-01[Word2Bits] Quantized Word Vectors | AISC
2017-11-15TMLS2017: Transitioning to Data Science, Panel Discussion


Tags:
deep learning
physics
learning representation