A foundational principle of connectionism is that perception, action, and cognition emerge from parallel computations among simple, interconnected units that generate and rely on neural representations. Accordingly, researchers employ multivariate pattern analysis to decode and compare the neural codes of artificial an...
Lukas Braun, Erin Grant, Andrew M. Saxe· 0 citations
It is argued that NeuroAI, neuroscience-informed artificial intelligence, has the potential to overcome limitations of current AI while deepening the authors' understanding of biological neural computation, and requires a new generation of researchers trained across the boundary between neuroscience and engineering.
A. Zador, J. Fellous, Terrence J. Sejnowski et al.· arXiv.org· 3 citations
This work extends MOP to partially observable environments and introduces a Bellman reformulation of the Expected Free Energy for Active Inference, both incorporating belief-based inference over hidden states as part of the agent state.
APST is presented, an Association Profile-conditioned Set-Temporal transformer that adapts to new sessions with all network weights frozen, and summarizes how each unit's firing relates to behavior in a four-dimensional association profile computed in closed form.
Xin-Yuan Zhang, Han-Dong Mo, Peng-Fei Wen et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Studying the alignment between the internal representations of vision models and the responses of the visual cortex to the same observed visual stimuli has enabled us to better understand human visual processing. However, studies so far have largely overlooked the fact that the human brain not only processes observed v...
TERRA provides a practical route from scene-less motion data to muscle-actuated locomotion over diverse non-flat terrain and improves terrain accuracy, sharply reduces anatomical and interaction violations, and achieves the highest observed completion rate over supported terrain families.
Merkourios Simos, Chengkun Li, Bianca Ziliotto et al.· 0 citations
Three findings emerge: in the restless task, neural models trained without rewards predict held-out choices better than four simple training-fitted behavioral baselines, and at some reward weights, neural networks predict better than a pooled reinforcement-learning model but have less faithful changes in choice probabi...
Sparse Autoencoders (SAEs) have found success parsing neural network representations into interpretable concepts, providing a basis for understanding and control. However, what exactly SAEs extract and, hence, the scientific conclusions we can draw from them are not obvious. In short, if your SAE behaves strangely, doe...
Recent frontier models mimic complex aspects of human cognition. Here we ask whether this alignment extends into reward valuation, which we assess in a mechanistic framework. Specifically, we use clinical tests that were developed to evaluate anhedonia in human subjects with major depressive disorders. Mechanistically,...
Melika Honarmand, Samin Mahdipour Aghabagher, Martin Schrimpf· 0 citations
An ongoing challenge in sensory neuroscience is to characterize the feature dimensions encoded by cortical populations. Recent approaches probe feature selectivity in a data-driven way, by synthesizing a most-exciting-input (MEI) for a target neural population. While this approach has been successfully applied to human...
Jun-Ru Zhao, Han-Fei Guo, Andrew F. Luo et al.· 0 citations
On a single task, deep neural networks can learn a wide range of solutions, depending on their optimizer, training data, architecture, and hyperparameters. Many of these solutions are surprisingly mode-connected: rather than isolated points in the weight space, they are connected by low loss regions. Despite this obser...
Ann C. Huang, Mitchell Ostrow, Zhou-Yang Lu et al.· arXiv.org· 0 citations
This paper critically examines the foundational assumptions of rational decision-making models and finds them to be systematically and comprehensively flawed. Through a rigorous analysis of empirical evidence from behavioral economics and neuroscience, we demonstrate that traditional models, such as Expected Utility Th...
Kwan Hong TAN· Zenodo (CERN European Organi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
