159 citations · 178 across the 12 of their papers we have counts for
14 papers
Task-driven Processing with Coarse-to-Fine Glimpse-based Active Perception
Oleh Kolner, Thomas Ortner, Stanisław Woźniak +1
State-of-the-art vision models process images in their entirety, lacking the ability to selectively zoom in on relevant regions. This limitation is particularly acute in scenarios…
FlowState: Sampling-Rate-Equivariant Time-Series Forecasting
Lars Graf, Thomas Ortner, Stanisław Woźniak +1
Existing time series foundation models (TSFMs), often based on transformer variants, lack adaptability to different sampling rates, struggle with generalization across varying cont…
Learning-to-learn enables rapid learning with phase-change memory-based in-memory computing
Thomas Ortner, Horst Petschenig, Athanasios Vasilopoulos +7
There is a growing demand for low-power, autonomously learning artificial intelligence (AI) systems that can be applied at the edge and rapidly adapt to the specific situation at d…
Intrinsic Biologically Plausible Adversarial Robustness
Matilde Tristany Farinha, Thomas Ortner, Giorgia Dellaferrera +2
Artificial Neural Networks (ANNs) trained with Backpropagation (BP) excel in different daily tasks but have a dangerous vulnerability: inputs with small targeted perturbations, als…
High-performance deep spiking neural networks with 0.3 spikes per neuron
Ana Stanojevic, Stanisław Woźniak, Guillaume Bellec +3
Communication by rare, binary spikes is a key factor for the energy efficiency of biological brains. However, it is harder to train biologically-inspired spiking neural networks (S…
Online Spatio-Temporal Learning with Target Projection
Thomas Ortner, Lorenzo Pes, Joris Gentinetta +2
Recurrent neural networks trained with the backpropagation through time (BPTT) algorithm have led to astounding successes in various temporal tasks. However, BPTT introduces severe…
Neuromorphic Optical Flow and Real-time Implementation with Event Cameras
Yannick Schnider, Stanislaw Wozniak, Mathias Gehrig +5
Optical flow provides information on relative motion that is an important component in many computer vision pipelines. Neural networks provide high accuracy optical flow, yet their…
Dynamic Event-based Optical Identification and Communication
Axel von Arnim, Jules Lecomte, Naima Elosegui Borras +2
Optical identification is often done with spatial or temporal visual pattern recognition and localization. Temporal pattern recognition, depending on the technology, involves a tra…
An Exact Mapping From ReLU Networks to Spiking Neural Networks
Ana Stanojevic, Stanisław Woźniak, Guillaume Bellec +3
Deep spiking neural networks (SNNs) offer the promise of low-power artificial intelligence. However, training deep SNNs from scratch or converting deep artificial neural networks t…
On the visual analytic intelligence of neural networks
Stanisław Woźniak, Hlynur Jónsson, Giovanni Cherubini +2
Visual oddity task was conceived as a universal ethnic-independent analytic intelligence test for humans. Advancements in artificial intelligence led to important breakthroughs, ye…
Towards efficient end-to-end speech recognition with biologically-inspired neural networks
Thomas Bohnstingl, Ayush Garg, Stanisław Woźniak +3
Automatic speech recognition (ASR) is a capability which enables a program to process human speech into a written form. Recent developments in artificial intelligence (AI) have led…
Learning in Deep Neural Networks Using a Biologically Inspired Optimizer
Giorgia Dellaferrera, Stanislaw Wozniak, Giacomo Indiveri +2
Plasticity circuits in the brain are known to be influenced by the distribution of the synaptic weights through the mechanisms of synaptic integration and local regulation of synap…
Online Spatio-Temporal Learning in Deep Neural Networks
Thomas Bohnstingl, Stanisław Woźniak, Wolfgang Maass +2
Biological neural networks are equipped with an inherent capability to continuously adapt through online learning. This aspect remains in stark contrast to learning with error back…
Deep learning incorporating biologically-inspired neural dynamics
Stanisław Woźniak, Angeliki Pantazi, Thomas Bohnstingl +1
Neural networks have become the key technology of artificial intelligence and have contributed to breakthroughs in several machine learning tasks, primarily owing to advances in de…