Sorry, you need to enable JavaScript to visit this website.

Canonical correlation analysis (CCA) is a classic statistical method for discovering latent co-variation that underpins two or more observed random vectors. Several extensions and variations of CCA have been proposed that have strengthened our capabilities in terms of revealing common random factors from multiview datasets. In this work, we first revisit the most recent deterministic extensions of deep CCA and highlight the strengths and limitations of these state-of-the-art methods. Some methods allow trivial solutions, while others can miss weak common factors.

As new technologies spread, phone fraud crimes have become master strategies to steal money and personal identities. Inspired by website authentication, we propose an end-to-end data modem over voice channels that can transmit the caller’s digital certificate to the callee for verification. Without assistance from telephony providers, it is difficult to carry useful information over voice channels. For example, voice activity detection may quickly classify the encoded signals as nonspeech signals and reject the input waveform.

Partially Observable Markov Decision Process (POMDP) is a general framework for a wide range of control tasks, which can benefit from enabling semantic communicatons among different agents. Semantic communications aim to exchange compact messages that can convey task-relevant information between agents. A critical problem in semantic communication is source representation learning, which is governed by a fundamental tradeoff between compactness and sufficiency. Such a tradeoff is still underinvestigated in the context of POMDP.

Cross-domain few-shot classification (CDFSC) is a challenging and tough task due to the significant distribution discrepancies across different domains. To address this challenge, many approaches aim to learn transferable representations. Multilayer perceptron (MLP) has shown its capability to learn transferable representations in various downstream tasks, such as unsupervised image classification and supervised concept generalization. However, its potential in the few-shot settings has yet to be comprehensively explored.

Despite the increasing attack ability and transferability of adversarial examples (AE), their security, i.e., how unlikely they can be detected, has been ignored more or less. Without the ability to circumvent popular detectors, the chance that an AE successfully fools a deep neural network is slim. This paper gives a game theory analysis of the interplay between an AE attacker and an AE detection investigator. Taking the perspective of a third party, we introduce a game theory model to evaluate the ultimate performance when both the attacker and the investigator are aware of each other.

We consider solving ill-posed imaging inverse problems without access to an explicit image prior or ground-truth examples. An overarching challenge in inverse problems is that there are many undesired images that fit to the observed measurements, thus requiring image priors to constrain the space of possible solutions to more plausible reconstructions. However, in many applications it is difficult or potentially impossible to obtain ground-truth images to learn an image prior. Thus, inaccurate priors are often used, which inevitably result in biased solutions.

Multi-task learning has attracted much attention due to growing multi-purpose research with multiple related data sources. Moreover, transduction with matrix completion is a useful method in multi-label learning. In this paper, we propose a transductive matrix completion algorithm that incorporates a calibration constraint for the features under the multi-task learning framework. The proposed algorithm recovers the incomplete feature matrix and target matrix simultaneously. Fortunately, the calibration information improves the completion results.

In the last couple of years, supervised machine learning (ML) methods have shown state-of-the-art results for near-ground rain estimation. Information is usually obtained from two kinds of sensors - rain gauges, which measure rain rate, and commercial microwave links (CMLs) which measure attenuation. These data sources are paired to create a dataset on which a model is trained.
The arising problem of such methods of training is in the need for the datasets to be constructed with a CML-rain gauge pairing relation.

Artificial Intelligent (AI) tools can be useful to address model deficits in the design of communication systems. However, conventional learning-based AI algorithms yield poorly calibrated decisions, unabling to quantify their outputs uncertainty. While Bayesian learning can enhance calibration by capturing epistemic uncertainty caused by limited data availability, formal calibration guarantees only hold under strong assumptions about the ground-truth, unknown, data generation mechanism.