Related papers: A Turing Test for Artificial Nets devoted to model…
Most chemical processes, such as distillation, absorption, extraction, and catalytic reactions, are extremely complex processes that are affected by multiple factors. The relationships between their input variables and output variables are…
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…
Three decades ago, Atick et al. suggested that human frequency sensitivity may emerge from the enhancement required for a more efficient analysis of retinal images. Here we reassess the relevance of low-level vision tasks in the explanation…
Vision-Language Models (VLMs) have achieved remarkable progress across tasks such as visual question answering and image captioning. Yet, the extent to which these models perform visual reasoning as opposed to relying on linguistic priors…
While foundation models have achieved remarkable results across a diversity of domains, they still rely on human-generated data, such as text, as a fundamental source of knowledge. However, this data is ultimately the product of human…
A hallmark of human intelligence is the ability to infer abstract rules from limited experience and apply these rules to unfamiliar situations. This capacity is widely studied in the visual domain using the Raven's Progressive Matrices.…
We propose Trusted Neural Network (TNN) models, which are deep neural network models that satisfy safety constraints critical to the application domain. We investigate different mechanisms for incorporating rule-based knowledge in the form…
Transfer learning has become the de facto standard in computer vision and natural language processing, especially where labeled data is scarce. Accuracy can be significantly improved by using pre-trained models and subsequent fine-tuning.…
Face recognition research is one of the most active topics in computer vision (CV), and deep neural networks (DNN) are now filling the gap between human-level and computer-driven performance levels in face verification algorithms. However,…
Subjective image quality measures based on deep neural networks are very related to models of visual neuroscience. This connection benefits engineering but, more interestingly, the freedom to optimize deep networks in different ways, make…
Connecting neural activity to function is a common aim in neuroscience. How to define and conceptualize function, however, can vary. Here I focus on grounding this goal in the specific question of how a given change in behavior is produced…
Artificial and natural neural network models are a new toolkit which could be potentially have been used for clarifying of complex brain functions. To attend this goal, such models need to be neurobiologically realistic. However, although…
Artificial neural network (ANN) is a supervised learning algorithm, where parameters are learned by several back-and-forth iterations of passing the inputs through the network, comparing the output with the expected labels, and correcting…
Bridging continuous perceptual signals and discrete symbolic reasoning is a fundamental challenge in AI systems that must operate under uncertainty. We present a neuro-symbolic framework that explicitly models and propagates uncertainty…
An essential problem in artificial intelligence is whether LLMs can simulate human cognition or merely imitate surface-level behaviors, while existing datasets suffer from either synthetic reasoning traces or population-level aggregation,…
Spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments. However, current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency…
The neural underpinning of the biological visual system is challenging to study experimentally, in particular as the neuronal activity becomes increasingly nonlinear with respect to visual input. Artificial neural networks (ANNs) can serve…
Reinforcement Learning (RL) agents often exhibit learning behaviors that are not intuitively interpretable by human observers, which can result in suboptimal feedback in collaborative teaching settings. Yet, how humans perceive and…
Understanding the encoding and decoding mechanisms of dynamic neural responses to different visual stimuli is an important topic in exploring how the brain represents visual information. Currently, hierarchically deep neural networks (DNNs)…
Artificial neural networks (ANNs), while exceptionally useful for classification, are vulnerable to misdirection. Small amounts of noise can significantly affect their ability to correctly complete a task. Instead of generalizing concepts,…