Giacomo Spigler

Giacomo Spigler
Tilburg University | UVT · Department of Cognitive Science and Artificial Intelligence

PhD

About

19
Publications
4,261
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
295
Citations

Publications

Publications (19)
Preprint
Full-text available
To enable an ethical and legal use of machine learning algorithms, they must both be fair and protect the privacy of those whose data are being used. However, implementing privacy and fairness constraints might come at the cost of utility (Jayaraman & Evans, 2019; Gong et al., 2020). This paper investigates the privacy-utility-fairness trade-off in...
Preprint
Full-text available
Efficient automated scheduling of trains remains a major challenge for modern railway systems. The underlying vehicle rescheduling problem (VRSP) has been a major focus of Operations Research (OR) since decades. Traditional approaches use complex simulators to study VRSP, where experimenting with a broad range of novel ideas is time consuming and h...
Article
Full-text available
Nowadays, lower-limb prostheses are reaching real-world usability especially on ground-level walking. However, some key tasks such as stair walking are still quite demanding. Providing haptic feedback about the foot placement on the steps might reduce the cognitive load of the task, compensating for increased dependency on vision and lessen the ris...
Article
Full-text available
The effectiveness of haptic feedback devices highly depends on the perception of tactile stimuli, which differs across body parts and can be affected by movement. In this study, a novel wearable sensory feedback apparatus made of a pair of pressure-sensitive insoles and a belt equipped with vibrotactile units is presented; the device provides time-...
Preprint
Full-text available
Current training regimes for deep learning usually involve exposure to a single task / dataset at a time. Here we start from the observation that in this context the trained model is not given any knowledge of anything outside its (single) training distribution, and has thus no way to learn parameters (i.e., feature detectors or policies) that coul...
Preprint
Full-text available
The key question we want to answer here is: How can trains learn to automatically coordinate among themselves, so that there are minimal delays in large train networks? - The Flatland Challenge is a competition to foster progress in multi-agent reinforcement learning for any re-scheduling problem (RSP). The challenge addresses a real-world problem...
Article
Full-text available
This study investigates the trade-off between computational efficiency and accuracy of Izhikevich neuron models by numerically quantifying their convergence to provide design guidelines in choosing the limit time steps during a discretization procedure. This is important for bionic engineering and neuro-robotic applications where the use of embedde...
Chapter
Lower limb prosthesis performance determines the quality of life of amputee patients. Such performance will benefit from a feedback informing the patient about the gait phase and the overall condition of the foot. This study reports the design and validation of a wearable haptic feedback system conceived to assist lower-limb amputees in various loc...
Chapter
Sensory feedback systems can improve gait performance of lower-limb amputees by providing information about the foot-ground interaction force. This study presents a new platform designed to deliver bilateral vibrations on the waist of the user, synchronously with specific gait events. Preliminary perceptual tests were carried out on five healthy su...
Conference Paper
Full-text available
Provided significant future progress in artificial intelligence and computing, it may ultimately be possible to create multiple Artificial General Intelligences (AGIs), and possibly entire societies living within simulated environments. In that case, it should be possible to improve the problem solving capabilities of the system by increasing the s...
Conference Paper
Full-text available
Provided significant future progress in artificial intelligence and computing, it may ultimately be possible to create multiple Artificial General Intelligences (AGIs), and possibly entire societies living within simulated environments. In that case, it should be possible to improve the problem solving capabilities of the system by increasing the s...
Article
Full-text available
Despite the recent developments that allowed neural networks to achieve impressive performance on a variety of applications, these models are intrinsically affected by the problem of overgeneralization, due to their partitioning of the full input space into the fixed set of target classes used during training. Thus it is possible for novel inputs b...
Article
Full-text available
Repetition suppression refers to a reduction in the cortical response to a novel stimulus that results from repeated presentation of the stimulus. We demonstrate repetition suppression in a well established computational model of cortical plasticity, according to which the relative strengths of lateral inhibitory interactions are modified by Hebbia...
Data
Supplementary materials and methods. Table of parameters and description of the homeostatic mechanisms used in pre-training. (PDF)
Data
Supplementary results. Exploration of the limit cases in which plasticity is restricted to either the afferent or inhibitory interactions in the model. (PDF)
Preprint
Full-text available
This study aims to numerically quantify the convergence of Izhikevich neuron model using a non-Euclidean metric-space analysis of spike sequences and thus provides information in choosing an optimal time step during discretization process. Implemented in MATLAB, the regular spiking (RS) Izhikevich neuron model as an example, we have compared conver...
Article
Full-text available
Restoration of touch after hand amputation is a desirable feature of ideal prostheses. Here, we show that texture discrimination can be artificially provided in human subjects by implementing a neuromorphic real-time mechano-neuro-transduction (MNT), which emulates to some extent the firing dynamics of SA1 cutaneous afferents. The MNT process was u...
Thesis
Full-text available
The present work investigates the neural mechanisms underlying the McCollough Effect through the simulation of three different models of color visual systems: a dichromatic and a trichromatic one that are inspired to the anatomy of the primates’ visual system and an idealised trichromatic model designed to aid the self-organization of a simulated P...
Conference Paper
Full-text available
We propose an artificial mechanotransduction system based on a 2×2 MEMS array touch sensor, and evaluate a neural model which is designed to convert raw sensor outputs into neural spike-trains. We show that core tactile information is preserved in the neural representation, and that the resulting modulation via spikes can be used in surface discrim...

Projects

Project (1)