Deep Learning
APPENDIX A Backpropagation in neural networks
We describe the nonlinearities we employed in appendix H.
Relative gradient optimization of the Jacobian term in unsupervised deep learning Luigi Gresele
Learning expressive probabilistic models correctly describing the data is a ubiquitous problem in machine learning.
Scalarization for Multi-Task and Multi-Domain Learning at Scale Amรฉlie Royer, Tijmen Blankevoort, Babak Ehteshami Bejnordi Qualcomm AI Research Amsterdam, The Netherlands
It also enables potential positive knowledge transfer across tasks/domains, leading to improved accuracy and data-efficient training.
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning
Continual learning agents experience a stream of (related) tasks.
ELIAS: End-to-End Learning to Index and Search in Large Output Spaces
A popular approach for dealing with the large label space is to arrange the labels into a shallow tree-based index and then learn an ML model to efficiently search this index via beam search.
A General Implementation Details For our Atari games and DeepMind Control Suite experiments, we largely follow DrQ [ 33
The replay buffer size is 100K. This procedure is repeated every time an image is sampled from the replay buffer. Batch size used in both RL and representation learning is 512. The corresponding hyperparameters used in Atari experiments are shown in Table 7 and Table 8. The action repeat hyperparameters are show in Table 6.
Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding Lin Lan
Additionally, we introduce an embedding transformation function that remedies the deficiency of the straightforward use of meta-learning.
Gaussian Gated Linear Networks David Budden Adam H. Marblestone Eren Sezener T or Lattimore Greg Wayne Joel V eness
We propose the Gaussian Gated Linear Network (G-GLN), an extension to the recently proposed GLN family of deep neural networks.
The Image Local Autoregressive Transformer
Thus iLA T can efficiently synthesize the local image regions by key guidance information.
Graph Neural Networks with Adaptive Readouts
An effective aggregation of node features into a graph-level representation via readout functions is an essential step in numerous learning tasks involving graph neural networks.