Wallonia
- North America > United States > California > San Francisco County > San Francisco (0.14)
- Asia > Middle East > Jordan (0.04)
- North America > United States > California > Santa Barbara County > Santa Barbara (0.04)
- Europe > Belgium > Wallonia > Walloon Brabant > Louvain-la-Neuve (0.04)
GAVEL: Generating Games Via Evolution and Language Models Graham T odd New York University Tandon Brooklyn, New York, USA gdrtodd Alexander G. Padula ETH Zurich Zurich, Switzerland apadula
Automatically generating novel and interesting games is a complex task.
- Europe > Switzerland > Zürich > Zürich (1.00)
- North America > United States > New York > Kings County > New York City (0.40)
- Europe > Germany (0.04)
- (8 more...)
- North America > Canada > Ontario > Toronto (0.14)
- North America > United States > South Dakota > Minnehaha County > Sioux Falls (0.04)
- Europe > Netherlands > South Holland > Delft (0.04)
- (4 more...)
- Energy (0.93)
- Information Technology (0.67)
- Transportation > Infrastructure & Services (0.46)
How a student becomes a teacher: learning and forgetting through Spectral methods
The above scheme proves particularly relevant when the student network is overparameterized (namely, when larger layer sizes are employed) as compared to the underlying teacher network. Under these operating conditions, it is tempting to speculate that the student ability to handle the given task could be eventually stored in a sub-portion of the whole network.
- North America > United States > California (0.04)
- North America > United States > Massachusetts > Middlesex County > Cambridge (0.04)
- Europe > Belgium > Wallonia > Namur Province > Namur (0.04)
How a student becomes a teacher: learning and forgetting through Spectral methods
The above scheme proves particularly relevant when the student network is overparameterized (namely, when larger layer sizes are employed) as compared to the underlying teacher network. Under these operating conditions, it is tempting to speculate that the student ability to handle the given task could be eventually stored in a sub-portion of the whole network.
- North America > United States > California (0.04)
- North America > United States > Massachusetts > Middlesex County > Cambridge (0.04)
- Europe > Belgium > Wallonia > Namur Province > Namur (0.04)
Learning Cut Generating Functions for Integer Programming
CGF can outperform the GMI cuts for certain distributions.
- North America > United States > Maryland > Baltimore (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- North America > United States > California (0.04)
- Europe > Belgium > Wallonia > Liège Province > Liège (0.04)
- Europe > Belgium > Wallonia > Namur Province > Namur (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- Europe > Belgium > Flanders > Antwerp Province > Antwerp (0.04)
- Asia > India (0.04)
- North America > United States > California > Santa Clara County > Palo Alto (0.04)
- North America > United States > District of Columbia (0.04)
- Europe > Belgium > Wallonia > Namur Province > Namur (0.04)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Search (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Logic & Formal Reasoning (1.00)
- Information Technology > Artificial Intelligence > Natural Language (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)
neurips_2021_main
Made: Maskedautoencoder fordistributionestimation. In Francis Bachand David Blei, editors,Proceedingsofthe 32nd International Conferenceon Machine Learning, volume 37 ofProceedingsof Machine Learning Research, pages 881-889, Lille, France, 07-09 Jul 2015.
- Europe > France > Hauts-de-France > Nord > Lille (0.24)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.05)
- Asia > Middle East > Jordan (0.05)
- (3 more...)
- Asia > South Korea > Seoul > Seoul (0.04)
- Europe > Russia (0.04)
- Europe > France (0.04)
- (3 more...)