Deep Learning
New computational algorithms make it possible to build neural networks with many input nodes and many layers, and distinguish "deep learning" of these networks from previous work on artificial neural nets.
Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices
Neural Information Processing Systems
Training deep neural networks on large datasets can often be accelerated by using multiple compute nodes.
Country:
- Asia > Russia (0.14)
- North America > Canada > Ontario > Toronto (0.14)
- North America > United States > Massachusetts (0.04)
- (2 more...)
Industry:
- Health & Medicine (0.67)
- Information Technology > Services (0.46)
- Energy (0.45)
Technology:
Country:
- Asia > Russia (0.14)
- North America > Canada > Ontario > Toronto (0.14)
- North America > United States > New York > New York County > New York City (0.04)
- (3 more...)
Industry:
- Health & Medicine (0.67)
- Information Technology (0.46)
Technology:
Country:
- Oceania > Australia (0.04)
- North America > United States > New York > New York County > New York City (0.04)
- South America > Colombia (0.04)
- (4 more...)
Genre:
- Research Report > Experimental Study (1.00)
- Research Report > New Finding (0.94)
Industry:
- Health & Medicine > Therapeutic Area > Dermatology (1.00)
- Health & Medicine > Therapeutic Area > Oncology (0.68)
Technology:
- Information Technology > Artificial Intelligence > Representation & Reasoning > Uncertainty (0.46)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.46)
Country:
- North America > United States > New York > New York County > New York City (0.05)
- North America > United States > California (0.04)
- South America > Colombia (0.04)
- (6 more...)
Genre:
- Research Report > Experimental Study (1.00)
- Research Report > New Finding (0.94)
Industry:
- Health & Medicine > Health Care Providers & Services (0.93)
- Health & Medicine > Therapeutic Area > Dermatology (0.69)
- Health & Medicine > Diagnostic Medicine (0.68)
Technology:
- Information Technology > Artificial Intelligence > Representation & Reasoning (1.00)
- Information Technology > Data Science > Data Mining (0.93)
- Information Technology > Artificial Intelligence > Natural Language (0.68)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.46)
Country:
- North America > United States > Illinois > Cook County > Chicago (0.04)
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
Technology:
- Information Technology > Artificial Intelligence > Vision (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning (0.94)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (0.94)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.46)
APPENDIX A Backpropagation in neural networks
Neural Information Processing Systems
We describe the nonlinearities we employed in appendix H.
Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.46)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Backpropagation (0.42)
Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift Christina Baek
Neural Information Processing Systems
OOD benchmarks -- a phenomenon they dubbed "accuracy-on-the-line".
Country:
- North America > Canada > Ontario > Toronto (0.14)
- Asia > Middle East > Lebanon (0.04)
- North America > United States > Virginia > Arlington County > Arlington (0.04)
- (4 more...)
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning
Neural Information Processing Systems
Continual learning agents experience a stream of (related) tasks.
Country:
- Asia > Japan > Honshลซ > Kansai > Osaka Prefecture > Osaka (0.45)
- North America > Canada > Quebec > Montreal (0.14)
- Europe > Germany > North Rhine-Westphalia > Upper Bavaria > Munich (0.04)
Genre:
- Instructional Material (0.46)
- Research Report > New Finding (0.46)
Industry:
- Education (0.93)
- Health & Medicine (0.68)
Technology:
- Information Technology > Data Science > Data Mining (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Undirected Networks > Markov Models (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.68)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Personal Assistant Systems (0.68)
Country:
- North America > United States > Wisconsin > Dane County > Madison (0.04)
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
- Asia > China > Zhejiang Province (0.04)
- Asia > China > Shaanxi Province > Xi'an (0.04)
Technology:
Pareto Set Learning for Expensive Multi-Objective Optimization
Neural Information Processing Systems
It is desirable to obtain an approximate Pareto front with a limited evaluation budget.
Country:
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- Asia > China > Hong Kong (0.04)
- Europe > Netherlands > South Holland > Leiden (0.04)
Technology:
- Information Technology > Artificial Intelligence > Representation & Reasoning > Optimization (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.46)