Home /

Research

Showing 307 - 312 / 904

Energy-Based Models for Continual Learning

Authors:  ShuangLi, YilunDu, GidoM.vandeVen....
Published date-11/24/2020
Tasks:  ContinualLearning

Abstract: We motivate Energy-Based Models (EBMs) as a promising model class for continual learning problems. Instead of tackling continual learning via the use of external memory, growing models, or regularization, EBMs …
Paper Code

DeepShadows: Separating Low Surface Brightness Galaxies from Artifacts using Deep Learning

Authors:  DimitriosTanoglidis, AleksandraĆiprijanović, AlexDrlica-Wagner....
Published date-11/24/2020
Tasks:  TransferLearning

Abstract: Searches for low-surface-brightness galaxies (LSBGs) in galaxy surveys are plagued by the presence of a large number of artifacts (e.g., objects blended in the diffuse light from stars and galaxies, …
Paper Code

Argument from Old Man's View: Assessing Social Bias in Argumentation

Authors:  MaximilianSpliethöver, HenningWachsmuth....
Published date-11/24/2020
Tasks:  WordEmbeddings

Abstract: Social bias in language - towards genders, ethnicities, ages, and other social groups - poses a problem with ethical impact for many NLP applications. Recent research has shown that machine …
Paper Code

Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis

Authors:  MichaelA.Lepori....
Published date-11/24/2020
Tasks:  WordEmbeddings

Abstract: We present a new approach for detecting human-like social biases in word embeddings using representational similarity analysis. Specifically, we probe contextualized and non-contextualized embeddings for evidence of intersectional biases against …
Paper Code

Language Generation via Combinatorial Constraint Satisfaction: A Tree Search Enhanced Monte-Carlo Approach

Authors:  MaosenZhang, NanJiang, LeiLI....
Published date-11/24/2020
Tasks:  LanguageModelling, TextGeneration

Abstract: Generating natural language under complex constraints is a principled formulation towards controllable text generation. We present a framework to allow specification of combinatorial constraints for sentence generation. We propose TSMH, …
Paper Code

PeleNet: A Reservoir Computing Framework for Loihi

Authors:  CarloMichaelis....
Published date-11/24/2020

Abstract: High-level frameworks for spiking neural networks are a key factor for fast prototyping and efficient development of complex algorithms. Such frameworks have emerged in the last years for traditional computers, …
Paper Code

Filter by

Categories

Tags