Search Results for author:
Found 4 papers, 3 papers with code
CLASSP: a Biologically-Inspired Approach to Continual Learning through Adjustment Suppression and Sparsity Promotion
However, this principle results in a diffuse distribution of updates throughout the model, as it promotes updates for weights that haven’t been previously updated, while a sparse update distribution is preferred to leave weights unassigned for future tasks.
End-to-end Adversarial Learning for Generative Conversational Agents
This paper presents a new adversarial learning method for generative conversational agents (GCA) besides a new model of GCA.
Deep Learning with Eigenvalue Decay Regularizer
Moreover, we extend our previous theoretical analysis to deep neural networks and multiclass classification problems.
Deep Embedding for Spatial Role Labeling
This paper introduces the visually informed embedding of word (VIEW), a continuous vector representation for a word extracted from a deep neural model trained using the Microsoft COCO data set to forecast the spatial arrangements between visual objects, given a textual description.
