Dealing with uncertainty is essential for e cient reinforcement learning.

It then employs a novel decoding architecture, called Segment Detection Unit (SDU), that integrates the decoder state and encoder hidden states to detect segments sequentially.

Deep learning constructs are powerful tools for pattern matching and prediction.

Electronic health records provide a rich source of data for machine learning methods to learn dynamic treatment responses over time.

These embeddings are decoded by a single four-layer convolutional network to generate notes from nearly 1000 instruments, 65 pitches per instrument on average and 5 velocities.

We present a novel nonnegative tensor decomposition method, called Legendre decomposition, which factorizes an input tensor into a multiplicative combination of parameters. Thanks to the well-developed theory of information geometry, the reconstructed tensor is unique and always minimizes the KL divergence from an input tensor. We empirically show that Legendre decomposition can more accurately reconstruct tensors than other nonnegative tensor decomposition methods.

Channel pruning is one of the predominant approaches for deep model compression. Existing pruning methods either train from scratch with sparsity constraints on channels, or minimize the reconstruction error between the pre-trained feature maps and the compressed ones. Both strategies suffer from some limitations: the former kind is computationally expensive and difficult to converge, whilst the latter kind optimizes the reconstruction error but ignores the discriminative power of channels.

Novelty detection is the problem of identifying whether a new data point is considered to be an inlier or an outlier. We assume that training data is available to describe only the inlier distribution. Recent approaches primarily leverage deep encoder-decoder network architectures to compute a reconstruction error that is used to either compute a novelty score or to train a one-class classifier.

Most recent methods for learning-based, lossy image compression adopt an approach based on transform coding [1]. In this approach, image compression is achieved by first mapping pixel data into a quantized latent representation and then losslessly compressing the latents.

Neural Information Processing Systems http://nips.cc/