Search Results for author:
Found 7 papers, 5 papers with code
Maintaining Plasticity in Deep Continual Learning
If deep-learning systems are applied in a continual learning setting, then it is well known that they may fail to remember earlier examples.
Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning
Tomorrow's robots will need to distinguish useful information from noise when performing different tasks.
Continual Backprop: Stochastic Gradient Descent with Persistent Randomness
The Backprop algorithm for learning in neural networks utilizes two mechanisms: first, stochastic gradient descent and second, initialization with small random weights, where the latter is essential to the effectiveness of the former.
Gamma-Nets: Generalizing Value Estimation over Timescale
By using the timescale as one of the estimator's inputs we can estimate value for arbitrary timescales.
Unsupervised Semantic Abstractive Summarization
Automatic abstractive summary generation remains a significant open problem for natural language processing.
Variational Inference via Transformations on Distributions
Variational inference methods often focus on the problem of efficient model optimization, with little emphasis on the choice of the approximating posterior.
Text Summarization using Abstract Meaning Representation
With an ever increasing size of text present on the Internet, automatic summary generation remains an important problem for natural language understanding.
