This paper presents a unified model to perform language and speaker recognition simultaneously and altogether. The model is based on a multi-task recurrent neural network where the output of one task is fed as the input of the other, leading to a collaborative learning framework that can improve both language and speaker recognition by borrowing information from each other. Our experiments demo...

This paper describes key concepts, approach and modelling details for preliminary safety (risk) assessment of human functions in complex systems controlled by a human operator or a group of operators. Human function consists of sequence of tasks and each task can be “abnormally” executed by human potentially leading to undesired events compromising system safety. Usually function reliability is...

Link prediction is addressed as an output kernel learning task through semi-supervised Output Kernel Regression. Working in the framework of RKHS theory with vectorvalued functions, we establish a new representer theorem devoted to semi-supervised least square regression. We then apply it to get a new model (POKR: Penalized Output Kernel Regression) and show its relevance using numerical experi...

In recent years, a plethora of approaches have been proposed to deal with the increasingly challenging task of multi-output regression. This study provides a survey on state-of-the-art multi-output regression methods, that are categorized as problem transformation and algorithm adaptation methods. In addition, we present the mostly used performance evaluation measures, publicly available data s...

Natural language programming has proven to be a very challenging task. We present a novel idea which suggests using crowdsourcing to do natural language programming. Our approach asks non-expert workers to provide input/output examples for a task defined in natural language form. We then use a Programming by Example system to induce the intended program from the input/output examples. Our early...

Many single-neuron recording studies have examined the degree to which the activity of primary motor cortex (M1) neurons is related to the kinematics and kinetics of various motor tasks. This has not been explored as extensively for arm movement-related neurons in posterior parietal cortex area 5. We recorded the activity of 78 proximal-arm-related neurons in area 5 of two monkeys while they us...

Many single-neuron recording studies have examined the degree to which the activity of primary motor cortex (M1) neurons is related to the kinematics and kinetics of various motor tasks. This has not been explored as extensively for arm movement-related neurons in posterior parietal cortex area 5. We recorded the activity of 78 proximal arm-related neurons in area 5 of two monkeys while they us...

This paper focuses on the effects of activating expected self as compared to the effects of activating the ought self. The expected self is a component of self-knowledge that pertains to the perception of one's capabilities and potentials. Two experimental studies compared participants' task performance after manipulating the momentary accessibility of the expected self vs. the ought self. In S...

This paper examines optimal incentive contracts in which an agent’s compensation can be based on both “input” measures closely related to an agent’s effort, and “output” measures closely related to the principal’s payoff. I argue that when the agent has specific knowledge (i.e. private information that is difficult to communicate) about how his actions contribute to the principal’s payoff, outp...

This notebook paper describes the four runs submitted by IRIT at TRECVid 2010 Semantic Indexing task. The four submitted runs can be described and compared as follows: • Run 4 – late fusion (weighted sum) of multiple audio-only classifiers output • Run 3 – context-aware re-rank of run 4 using hidden Markov model • Run 2 – context-aware late fusion of multiple audio classifiers output with hidde...