Mohamed Oubbati

Real-Time Emotion Recognition from Speech Using Echo State Networks

The goal of this work is to investigate real-time emotion recognition in noisy environments. Our approach is to solve this problem using novel recurrent neural networks called echo state networks (ESN). ESNs utilizing the sequential characteristics of biologically motivated modulation spectrum features are easy to train and robust towards noisy real world conditions. The standard Berlin Database of Emotional Speech is used to evaluate the performance of the proposed approach. The experiments reveal promising results overcoming known difficulties and drawbacks of common approaches.

Adaptive Critic Design with Echo State Network

In the present paper an application of a novel neural network architecture called Echo State Network (ESN) within the frame of a reinforcement learning scheme named Adaptive Critic Design (ACD) is proposed. Our aim is to investigate the possibility for on-line training of adaptive critic using the ESN architecture. In particular the application of this approach to mobile robot control is presented. Our preliminary results are encouraging and demonstrate that ESNs are good candidates for the on-line application of an ACD optimization approach due to their specific structure and fast training algorithm.

A neural framework for adaptive robot control

This paper investigates how dynamics in recurrent neural networks can be used to solve some specific mobile robot problems such as motion control and behavior generation. We have designed an adaptive motion control approach based on a novel recurrent neural network, called Echo state networks. The advantage is that no knowledge about the dynamic model is required, and no synaptic weight changing is needed in presence of time varying parameters in the robot. To generate the robot behavior over time, we adopted a biologically inspired approach called neural fields. Due to its dynamical properties, a neural field produces only one localized peak that indicates the optimum movement direction, which navigates a mobile robot to its goal in an unknown environment without any collisions with static or moving obstacles.

Neural Fields for Controlling Formation of Multiple Robots

In this paper we investigate how neural fields can produce an elegant solution for the problem of moving multiple robots in formation. The objective is to acquire a target, avoid obstacles and keep a geometric configuration at the same time. Several formations for a team of three robots are considered.

Learning robot-environment interaction using echo state networks

Learning robot-environment interaction with echo state networks (ESNs) is presented in this paper. ESNs are asked to bootstrap a robots control policy from human teachers demonstrations on the robot learner, and to generalize beyond the demonstration dataset. Benefits and problems involved in some navigation tasks are discussed, supported by real-world experiments with a small mobile robot.

Learning of embodied interaction dynamics with recurrent neural networks: some exploratory experiments

The new tendency of artificial intelligence suggests that intelligence must be seen as a result of the interaction between brains, bodies and environments. This view implies that designing sophisticated behaviour requires a primary focus on how agents are functionally coupled to their environments. Under this perspective, we present early results with the application of reservoir computing as an efficient tool to understand how behaviour emerges from interaction. Specifically, we present reservoir computing models, that are inspired by imitation learning designs, to extract the essential components of behaviour that results from agent-environment interaction dynamics. Experimental results using a mobile robot are reported to validate the learning architectures.

Real-Time Emotion Recognition Using Echo State Networks

The goal of this work is the exploration of real-time emotion recognition from speech. In this approach a novel type of recurrent neural networks called echo state networks (ESN) are utilized. Biologically motivated features representing modulations of the speech signal are used as input to the ESNs. The standard Berlin Database of Emotional Speech is used to evaluate the performance of the proposed approach. However, in this paper ongoing work is being presented and the final architecture has yet to be determined.

Adaptive Learning in Continuous Environment Using Actor-Critic Design and Echo-State Networks

Approximating adaptive dynamic programming has been studied extensively in recent years for its potential scalability to solve problems involving continuous state and action spaces. The framework of adaptive critic design (ACD) addresses this issue and has been demonstrated in several case studies. The present paper proposes an implementation of ACD using an echo state network as the critic. The ESN is trained online to estimate the utility function and adapt the control policy of an embodied agent. In addition to its simple training algorithm, the ESN structure facilitates backpropagation of derivatives needed for adapting the controller. Experimental results using a mobile robot are provided to validate the proposed learning architecture.

Neural fields for complex behavior generation on autonomous robots

In this paper we investigate how neural fields can generate complex behavior in mobile robot navigation. A case study is presented in which a mobile robot endowed with sonars and a laserscanner performs the behaviors target-acquisition, obstacle-avoidance, and subtarget-selection. The design of these behaviors as well as their coordination are achieved through correct choice of stimulus parameters on the field. We describe the approach in theoretical terms, supported by experimental results.

Intrinsically Motivated Decision Making for Situated, Goal-Driven Agents

Goal-driven agents are generally expected to be capable of pursuing simultaneously a variety of goals. As these goals may compete in certain circumstances, the agent must be able to constantly trade them off and shift their priorities in a rational way. One aspect of rationality is to evaluate its needs and make decisions accordingly. We endow the agent with a set of needs, or drives, that change over time as a function of external stimuli and internal consumption, and the decision making process hast to generate actions that maintain balance between these needs. The proposed framework pursues an approach in which decision making is considered as a multiobjective problem and approximately solved using a hierarchical reinforcement learning architecture. At a higher-level, a Q-learning learns to select the best learning strategy that improves the well-being of the agent. At a lower-level, an actor-critic design executes the selected strategy while interacting with a continuous, partially observable environment. We provide simulation results to demonstrate the efficiency of the approach.