We address the interpretability of convolutional neural networks (CNNs) for predicting a geo-location from an image. In a pilot experiment we classify images of Pittsburgh vs Tokyo and visualize the learned CNN filters. We found that varying the CNN architecture leads to variating in the visualized filters. This calls for further investigation of the effective parameters on the interpretability of CNNs.

Speech intelligibility enhancement is considered for multiple-microphone acquisition and single loudspeaker rendering. This is based on the mutual information measured between the message spoken at far-end environment and the message perceived by a listener at near-end. We prove that the joint optimal processing can be decomposed into far-end and near-end processing. The former is a minimum variance distortionless response beamformer that reduces the noise in the talker environment and the latter is a post-filter that redistributes the power over the frequency bands. Disjoint processing is optimal provided that the post-filtering operation is aware of the residual noise from the beamforming operation. Our results show that both processing steps are necessary for the effective conveyance of a message and, importantly, that the second step must be aware of the remaining noise from the beamforming operation in the first step. In addition, we study the use of the mutual information applied on the perceptually more relevant powers per critical band.

The combination of baseband and analog precoding for multiple-input multiple-output (MIMO) systems is considered in this paper which is referred to as hybrid precoding. The system capacity, as a design criterion, is maximized subject to unit modulus constraints on the elements of the analog precoder (phase shifters), and a total power constraint. This is a non-convex problem due to the product of the analog and baseband precoder variables. The proposed technique suggests computing non-trivial complex derivatives of the objective and constraints, analytically, in order to develop an iterative gradient-based sequential optimization algorithm to solve the non-convex problem. Promising simulation results show that the solution of the proposed algorithm is sufficiently close to the optimal (full-baseband) precoder solution, regardless of the channel characteristics.