Home /

Research

Showing 553 - 558 / 897

Investigating Learning in Deep Neural Networks using Layer-Wise Weight Change


Authors:  AyushManishAgrawal, AtharvaTendle, HarshvardhanSikka....
Published date-11/13/2020

Abstract: Understanding the per-layer learning dynamics of deep neural networks is of significant interest as it may provide insights into how neural networks learn and the potential for better training regimens. …

Efficient Subspace Search in Data Streams


Authors:  EdouardFouché, FlorianKalinke, KlemensBöhm....
Published date-11/13/2020
Tasks:  OutlierDetection

Abstract: In the real world, data streams are ubiquitous -- think of network traffic or sensor data. Mining patterns, e.g., outliers or clusters, from such data must take place in real …

Wisdom of the Ensemble: Improving Consistency of Deep Learning Models


Authors:  LijingWang, DipanjanGhosh, MariaTeresaGonzalezDiaz....
Published date-11/13/2020

Abstract: Deep learning classifiers are assisting humans in making decisions and hence the user's trust in these models is of paramount importance. Trust is often a function of constant behavior. From …

Multi-layered tensor networks for image classification


Authors:  RaghavendraSelvan, SilasØrting, ErikBDam....
Published date-11/13/2020
Tasks:  ImageClassification, TensorNetworks

Abstract: The recently introduced locally orderless tensor network (LoTeNet) for supervised image classification uses matrix product state (MPS) operations on grids of transformed image patches. The resulting patch representations are combined …

Image Animation with Perturbed Masks


Authors:  YoavShalev, LiorWolf....
Published date-11/13/2020
Tasks:  ImageAnimation

Abstract: We present a novel approach for image-animation of a source image by a driving video, both depicting the same type of object. We do not assume the existence of pose …

Testing the Genomic Bottleneck Hypothesis in Hebbian Meta-Learning


Authors:  RasmusBergPalm, EliasNajarro, SebastianRisi....
Published date-11/13/2020
Tasks:  Meta-Learning

Abstract: Recent work has shown promising results using Hebbian meta-learning to solve hard reinforcement learning problems and adapt-to a limited degree-to changes in the environment. In previous works each synapse has …

Filter by

Categories

Tags