About
25
Publications
5,702
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
411
Citations
Publications
Publications (25)
We introduce Proximal Policy Distillation (PPD), a novel policy distillation method that integrates student-driven distillation and Proximal Policy Optimization (PPO) to increase sample efficiency and to leverage the additional rewards that the student policy collects during distillation. To assess the efficacy of our method, we compare PPD with tw...
Objects, in particular tools, provide several action possibilities to the agents that can act on them, which are generally associated with the term of affordances. A tool is typically designed for a specific purpose, such as driving a nail in the case of a hammer, which we call as the primary affordance. A tool can also be used beyond its primary p...
Head movements are crucial for social human-human interaction. They can transmit important cues (e.g., joint attention, speaker detection) that cannot be achieved with verbal interaction alone. This advantage also holds for human-robot interaction. Even though modeling human motions through generative AI models has become an active research area wi...
Depression and anxiety disorders are prevalent mental health challenges affecting a substantial segment of the global population. In this study, we explored the environmental correlates of these disorders by analyzing street-view images (SVI) of neighborhoods in the Netherlands. Our dataset comprises 9,879 Dutch SVIs sourced from Google Street View...
In this study, we investigate the container delivery problem and explore ways to optimize the complex and nuanced system of inland container shipping. Our aim is to fulfill customer demand while maximizing customer service and minimizing logistics costs. To address the challenges posed by an unpredictable and rapidly-evolving environment, we examin...
Recent years have witnessed relevant advancements in the quality of life of persons with lower limb amputations thanks to the technological developments in prosthetics. However, prostheses that provide information about the foot–ground interaction, and in particular about terrain irregularities, are still missing on the market. The lack of tactile...
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...
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...
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...
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-...
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...
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...
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...
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...
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...
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...
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...
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...
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...
Supplementary materials and methods.
Table of parameters and description of the homeostatic mechanisms used in pre-training.
(PDF)
Supplementary results.
Exploration of the limit cases in which plasticity is restricted to either the afferent or inhibitory interactions in the model.
(PDF)
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...
ELife digest
Our hands provide us with a wide variety of information about our surroundings, enabling us to detect pain, temperature and pressure. Our sense of touch also allows us to interact with objects by feeling their texture and solidity. However, completely reproducing a sense of touch in artificial or prosthetic hands has proven challenging...
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...
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...