Related papers: Beyond Object-Level Alignment: Do Brains and DNNs …
Significant improvement has been made on just noticeable difference (JND) modelling due to the development of deep neural networks, especially for the recently developed unsupervised-JND generation models. However, they have a major…
Findings in recent years on the sensitivity of convolutional neural networks to additive noise, light conditions and to the wholeness of the training dataset, indicate that this technology still lacks the robustness needed for the…
Conformal symmetries, i.e.\ coordinate transformations that preserve angles, play a key role in many fields, including physics, mathematics, computer vision and (geometric) machine learning. Here we build a neural network that is…
Animals learn to predict external contingencies from experience through a process of conditioning. A natural mechanism for conditioning is stimulus substitution, whereby the neuronal response to a stimulus with no prior behavioral…
Modern deep neural networks tend to be evaluated on static test sets. One shortcoming of this is the fact that these deep neural networks cannot be easily evaluated for robustness issues with respect to specific scene variations. For…
Modern artificial neural networks, including convolutional neural networks and vision transformers, have mastered several computer vision tasks, including object recognition. However, there are many significant differences between the…
Dynamical systems models such as recurrent neural networks (RNNs) are increasingly popular in theoretical neuroscience for hypothesis-generation and data analysis. Evaluating the dynamics in such models is key to understanding their learned…
Spiking Neural Networks (SNNs) offer low-latency and energy-efficient decision making on neuromorphic hardware, making them attractive for Reinforcement Learning (RL) in resource-constrained edge devices. However, most RL algorithms for…
A central challenge in neuroscience is to understand neural computations and circuit mechanisms that underlie the encoding of ethologically relevant, natural stimuli. In multilayered neural circuits, nonlinear processes such as synaptic…
Visual object recognition -- the behavioral ability to rapidly and accurately categorize many visually encountered objects -- is core to primate cognition. This behavioral capability is algorithmically impressive because of the myriad…
We propose a novel approach to image classification inspired by complex nonlinear biological visual processing, whereby classical convolutional neural networks (CNNs) are equipped with learnable higher-order convolutions. Our model…
Visual reasoning is a long-term goal of vision research. In the last decade, several works have attempted to apply deep neural networks (DNNs) to the task of learning visual relations from images, with modest results in terms of the…
Variational Level Set (VLS) has been a widely used method in medical segmentation. However, segmentation accuracy in the VLS method dramatically decreases when dealing with intervening factors such as lighting, shadows, colors, etc.…
Event cameras, with their high dynamic range and temporal resolution, are ideally suited for object detection, especially under scenarios with motion blur and challenging lighting conditions. However, while most existing approaches…
In our invited talk at the AI Evaluation Workshop of the University of Bristol back in June 2022 we argued that, despite claims about successful modeling of the visual brain using ANNs, the problem is far from being solved (even for…
Detecting Beyond Standard Model (BSM) signals in high-energy particle collisions presents significant challenges due to complex data and the need to differentiate rare signal events from Standard Model (SM) backgrounds. This study…
Decoding visual stimuli from neural activity is essential for understanding the human brain. While fMRI methods have successfully reconstructed static images, fMRI-to-video reconstruction faces challenges due to the need for capturing…
Retinal image of surrounding objects varies tremendously due to the changes in position, size, pose, illumination condition, background context, occlusion, noise, and nonrigid deformations. But despite these huge variations, our visual…
While deep neural networks take loose inspiration from neuroscience, it is an open question how seriously to take the analogies between artificial deep networks and biological neuronal systems. Interestingly, recent work has shown that deep…
Convolutional Neural Networks (CNNs) exhibit a well-known texture bias, prioritizing local patterns over global shapes - a tendency inherent to their convolutional architecture. While this bias is beneficial for texture-rich natural images,…