A new framework, which resolves some of the known drawbacks of the Information Bottleneck. We provide a theoretical analysis of the framework, finding the structure of its solutions and present a novel variational formulation for DNNs.
Study the generalization properties of infinite ensembles of infinitely-wide neural networks. We report analytical and empirical investigations in the search for signals that correlate with generalization.
Analysing perceptual learning of pure tones in the auditory cortex. Using a novel computational model, we show that overrepresentation of the learned tones does not improve along the training.
A semi supervised model for detecting anomalies in videos inspiredby the Video Pixel Network. We extend the Convolutional LSTM video encoder of the VPN with a novel convolutional based attention. This approach could be a component in applications requiring visual common sense.
We extend the standard LSTM architecture by augmenting it with an additional gate which produces a memory control vector signal. This vector is fed back to the LSTM instead of the original output prediction. By decoupling the LSTM prediction from its role as a memory controller we allow each output to specialize in its own task.
We demonstrate the effectiveness of the Information-Plane visualization of DNNs. (i) Most of the training epochs are spent on compression of the input to efficient representation. (ii) The representation compression phase begins when the SGD steps change from a fast drift into a stochastic relaxation (iii) The converged layers lie very close to the information bottleneck theoretical bound, and the maps to the hidden layers satisfy the IB self-consistent equations (iv) The training time is dramatically reduced when adding more hidden layers.
A deep-learning based system, which performs real-time detection of diverse visual corruptions in videos. Developing this system involved challenging data science aspects to enable detection of small distortions with low false alert rates.