Modelling biologically-plausible neural structures for intelligent agents presents a unique challenge when operating in real-time domains. Neurons in our brains have different response properties, firing rates, and propagation lengths, creating noise that cannot be reliably decoded. This research explores the strengths and limitations of LIF spiking neuron ensembles for application in OpenAI virtual environments. Topics discussed include how we represent arbitrary environmental signals from multiple senses, choosing between equally viable actions in a given scenario, and how one can create a generic model that can learn and operate in a verity of situations.

Analysis of spontaneous speech is an important tool for clinical linguists to diagnose various dementia types that affect the language processing areas. Prosody is affected by some dementia types, most notably Parkinson's disease (PD, degradation of voice quality, unstable pitch), Alzheimer's disease (AD, monotonic pitch), and the non-fluent type of Primary Progressive Aphasia (PPA-NF, hesitant, non-fluent speech). Prosodic features can be computed efficiently by software. In this study, we evaluate the performance of a SVM classifier that is trained on prosodic features only. The limitation to only prosody yields baseline results that can be used in a later stage to evaluate the added effect of variables of (morpho) syntax. The goal is to distinguish different dementia types based on the recorded speech. Results show that the classifier can distinguish some dementia types (PPA-NF, AD), but not others (PD, PPA-SD).

English uses the passive voice more frequently than French. One method of translating the passive includes rendering the sentence as active by using an active verb, and changing the placement of the verb’s arguments. We are studying extra-syntactic features that predict where this method of translating the passive voice is used, in-cluding animacy and information status. We have obtained data from examining the Hansard, the transactions of the Canadian Parliament, which is published in both languages. This paper presents the results of a small mechanized corpus analysis on the relevance of the relative animacy of the agent (or experiencer) and the theme. This information will help to achieve desired stylistic output in a bilingual surface realizer.

This paper deals with extracting and learning patterns of assonance as a stylistic feature for author attribution of historical texts. We describe an assonance extraction algorithm, and consider results from an extensive set of machine learning experiments, based on a historical corpus of 18th century American and British texts. The results are compared with those obtained from the use of other prosodic and traditional stylistic features.

In this work we introduce the problem of incendiary news detection. We compare and contrast this problem with the problem of hate speech detection in social media. Most of the social media posts that are classified as hate speech contain straightforward slurs, insults, swearing, etc. In contrast to social media posts, incendiary news articles often do not contain any straightforward slurs and insults but, nevertheless, incite hate. To detect such news articles, we leverage are source where activists attempt to combat hate on-line by manually tagging the news articles inciting hate. We collect non-incendiary news by retrieving news articles from the websites of the news agencies which are recognized world-wide as serious media that are highly unlikely to contain foul language (BBC, CNN). We run a classification experiment using several classification approaches. We demonstrate that our system differentiates between incendiary and non-incendiary news with 97.0% accuracy. We ensure the validity of our approach by using two different non-incendiary news corpora.

Recent progress in AI and Reinforcement learning has shown great success in solving complex problems with high dimensional state spaces. However, most of these successes have been primarily in simulated environments where failure is of little or no consequence. Most real-world applications, however, require training solutions that are safe to operate as catastrophic failures are inadmissible especially when there is human interaction involved. Currently, Safe RL systems use human oversight during training and exploration in order to make sure the RL agent does not go into a catastrophic state. These methods require a large amount of human labor and it is very difficult to scale up. We present a hybrid method for reducing the human intervention time by combining model-based approaches and training a supervised learner to to improve sample efficiency while also ensuring safety. We evaluate these methods on various grid-world environments using both standard and visual representations and show that our approach achieves better performance in terms of sample efficiency, number of catastrophic states reached as well as overall task performance compared to traditional model-free approaches.

Taxi demand prediction has recently attracted increasing research interest due to its huge potential application in large-scale intelligent transportation systems. However, most of the previous methods only considered the taxi demand prediction in origin regions, but neglected the modeling of the specific situation of the destination passengers. We believe it is suboptimal to preallocate the taxi into each region based solely on the taxi origin demand. In this paper, we present a challenging and worth-exploring task, called taxi origin-destination demand prediction, which aims at predicting the taxi demand between all region pairs in a future time interval. Its main challenges come from how to effectively capture the diverse contextual information to learn the demand patterns. We address this problem with a novel Contextualized Spatial-Temporal Network (CSTN), which consists of three components for the modeling of local spatial context (LSC), temporal evolution context (TEC) and global correlation context (GCC) respectively. Firstly, an LSC module utilizes two convolution neural networks to learn the local spatial dependencies of taxi demand respectively from the origin view and the destination view. Secondly, a TEC module incorporates both the local spatial features of taxi demand and the meteorological information to a Convolutional Long Short-term Memory Network (ConvLSTM) for the analysis of taxi demand evolution. Finally, a GCC module is applied to model the correlation between all regions by computing a global correlation feature as a weighted sum of all regional features, with the weights being calculated as the similarity between the corresponding region pairs. Extensive experiments and evaluations on a large-scale dataset well demonstrate the superiority of our CSTN over other compared methods for taxi origin-destination demand prediction.

Recently, a number of learning-based optimization methods that combine data-driven architectures with the classical optimization algorithms have been proposed and explored, showing superior empirical performance in solving various ill-posed inverse problems, but there is still a scarcity of rigorous analysis about the convergence behaviors of learning-based optimization. In particular, most existing analyses are specific to unconstrained problems but cannot apply to the more general cases where some variables of interest are subject to certain constraints. In this paper, we propose Differentiable Linearized ADMM (D-LADMM) for solving the problems with linear constraints. Specifically, D-LADMM is a K-layer LADMM inspired deep neural network, which is obtained by firstly introducing some learnable weights in the classical Linearized ADMM algorithm and then generalizing the proximal operator to some learnable activation function. Notably, we rigorously prove that there exist a set of learnable parameters for D-LADMM to generate globally converged solutions, and we show that those desired parameters can be attained by training D-LADMM in a proper way. To the best of our knowledge, we are the first to provide the convergence analysis for the learning-based optimization method on constrained problems.

Building upon recent advances in entropy-regularized optimal transport, and upon Fenchel duality between measures and continuous functions , we propose a generalization of the logistic loss that incorporates a metric or cost between classes. Unlike previous attempts to use optimal transport distances for learning, our loss results in unconstrained convex objective functions, supports infinite (or very large) class spaces, and naturally defines a geometric generalization of the softmax operator. The geometric properties of this loss make it suitable for predicting sparse and singular distributions, for instance supported on curves or hyper-surfaces. We study the theoretical properties of our loss and show-case its effectiveness on two applications: ordinal regression and drawing generation.

In order to achieve it, we proposed and developed the classification framework EasiCS to obtain the relative stability The cervical spondylosis(CS), a common degenerative clustering results, which consists of dimension reduction, disease, harms human life and health, affects up clustering algorithm EasiSOM, spectral clustering algorithm to two-thirds of the population, and poses an serious EasiSC as shown in the Figure 1. To the best of our burden on individuals and society (Matz et al. 2009; knowledge, the EasiCS is the first effort to utilize the clustering Kotil and Bilge 2008; Cai et al. 2016; Nana Wang; algorithm and sEMG. Compared with the seven commonly Wang et al. 2018). Currently, the neck disability index used clustering algorithms, the novelty framework (Howard Vernon) is the most commonly used tool EasiCS provide the best overall performance. The cervical to assess the neck dysfunction (Vernon and Mior 1991), spondylosis(CS), a common degenerative disease, harms human The availability of which are mainly undermined by the life and health, affects up to two-thirds of the population, coarse-grained and unreasonable classification, despite that and poses an serious burden on individuals and society the NDI information is subjective and not accurate enough.