Deep Learning
Unsupervised Learning of Object Landmarks through Conditional Image Generation
Tomas Jakab, Ankush Gupta, Hakan Bilen, Andrea Vedaldi
Neural Information Processing Systems http://nips.cc/
Isolating Sources of Disentanglement in Variational Autoencoders
Tian Qi Chen, Xuechen Li, Roger B. Grosse, David K. Duvenaud
Neural Information Processing Systems http://nips.cc/
Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces
Yu-An Chung, Wei-Hung Weng, Schrasing Tong, James Glass
The framework consists of two steps.
Deep Predictive Coding Network with Local Recurrent Processing for Object Recognition
Kuan Han, Haiguang Wen, Yizhen Zhang, Di Fu, Eugenio Culurciello, Zhongming Liu
Inspired by "predictive coding" - a theory in neuroscience, we develop a bidirectional and dynamic neural network with local recurrent processing, namely
BRUNO: A Deep Recurrent Model for Exchangeable Data
Iryna Korshunova, Jonas Degrave, Ferenc Huszar, Yarin Gal, Arthur Gretton, Joni Dambre
We present a novel model architecture which leverages deep learning tools to perform exact Bayesian inference on sets of high dimensional, complex observations.
Heterogeneous Bitwidth Binarization in Convolutional Neural Networks
Joshua Fromm, Shwetak Patel, Matthai Philipose
Neural Information Processing Systems http://nips.cc/
Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders
Autowarp often outperforms hand-crafted trajectory similarity metrics.
Learning filter widths of spectral decompositions with wavelets
Time series classification using deep neural networks, such as convolutional neural networks (CNN), operate on the spectral decomposition of the time series computed using a preprocessing step.
A Bridging Framework for Model Optimization and Deep Propagation
However, generally designed schematic iterations may hard to investigate complex data distributions in real-world applications. Recently, training deep propagations (i.e., networks) has gained promising
Gradient Descent for Spiking Neural Networks
Dongsung Huh, Terrence J. Sejnowski
Research in spike-based computation has been impeded by the lack of efficient supervised learning algorithm for spiking neural networks.