ZUNINO R.

Artificial tactile systems can facilitate the life of people suffering from a loss of the sense of touch. These systems use sensors and digital, battery-operated embedded units for data processing. Therefore, low-power, resource-constrained devices should host those embedded devices. The paper presents a framework based on 1-D convolutional...

Learning paradigms that use random basis functions provide effective tools to deal with large datasets, as they combine efficient training algorithms with remarkable generalization performances. The paper first considers the affinity between the paradigm of learning with similarity functions and the Extreme Learning Machine (ELM) model, and...

Deep convolutional neural networks (CNNs) provide an effective tool to extract complex information from images. In the area of image polarity detection, CNNs are customarily utilized in combination with transfer learning techniques to tackle a major problem: the unavailability of large sets of labeled data. Thus, polarity predictors in general...

With the growth of pervasive electronics, the availability of compact digital circuitry for the support of data processing is becoming a key requirement. This paper tackles the design of a digital architecture supporting the n-mode tensormatrix product in fixed point representation. The design aims to minimize the resources occupancy, targeting...

Random-based learning paradigms exhibit efficient training algorithms and remarkable generalization performances. However, the computational cost of the training procedure scales with the cube of the number of hidden neurons. The paper presents a novel training procedure for random-based neural networks, which combines ensemble techniques and...

Image polarity detection opens new vistas in the area of pervasive computing. State-of-the-art frameworks for polarity detection often prove computationally demanding, as they rely on deep learning networks. Thus, one faces major issues when targeting their implementation on resource-constrained embedded devices. This paper presents a design...

This paper presents the T-RexNet approach to detect small moving objects in videos by using a deep neural network. T-RexNet combines the advantages of Single-Shot-Detectors with a specific feature-extraction network, thus overcoming the known shortcomings of Single-Shot-Detectors in detecting small objects. The deep convolutional neural network...

The deployment of connectionist models on resource-constrained, low-power embedded systems brings about specific implementation issues. The paper presents a design strategy, aimed at low-end reconfigurable devices, for implementing the prediction operation supported by a single hidden-layer feedforward neural network (SLFN). The paper first...

Affordance segmentation is used to split object images into parts according to the possible interactions, usually to drive safe robotic grasping. Most approaches to affordance segmentation are computationally demanding; this hinders their integration into wearable robots, whose compact structure typically offers limited processing power. The...

No description

Depth sensors play a major role in the control pipeline of semi-autonomous prostheses. The feed from these sensors can complement, or even substitute, the information retrieved by RGB cameras. The paper explores the application of depth sensors to affordance detection, to recognize the graspable part of an object in foreground images. The...