Category
134 papers
Associations between speech sounds and meaning are well documented but have not been systematically mapped over a whole alphabet. Here we map them across the 26 English letters and find that each carries a structured, multidimensional semantic profile that is recoverable from text, perceived across languages, and predi...
A neuroscience-informed SSL model based on PC and active perception that sidesteps the need for a generative model of sensory input by learning to predict representations of data across parallel streams, resulting in an encoder-only learning-and-inference scheme.
Continuous adaptive learning, the ability to adapt to the environment and keep improving performance, is a hallmark of natural intelligence. Biological organisms excel in acquiring, transferring, and retaining knowledge while adapting to volatile environments, making them a source of inspiration for artificial neural n...
Brain-computer interfaces (BCIs) decode neural activity into commands, yet most existing systems rely on fixed-window decoding that may result in redundant observation or unreliable predictions due to insufficient evidence. Adaptive temporal decision-making (ATDM) addresses this accuracy-time trade-off by progressively...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Sign differences suggest that a single comparator may not provide an architecture-invariant decomposition of a pretrained-versus-supervised performance gap, and validation-fitted temperature scaling returns foundation-model calibration error to the supervised range despite substantially lower four-class accuracy.
A compact, reusable representation for array-wide spiking activity without learned assay-specific parameters is established, providing a scalable foundation for generative modeling across diverse neural preparations.
BrainWideBench is presented, a benchmark for evaluating across-animal transfer on multi-region neural recordings, built on the International Brain Laboratory Brainwide Map dataset of neural and behavioral recordings spanning 276 brain regions from 139 mice performing a sensory-guided decision-making task.
2D and 3D videos could generally induce a higher cognitive load, but the extent of the differences also depended on the contents of the video stimuli and the viewing purpose, and the Cognitive Load Index (CLI) was introduced.
Fixed points of recurrent neural networks can be leveraged to store and generate information. These fixed points are captured by the Boltzmann-Gibbs measure, which leads to neural Langevin dynamics that relax to those fixed points for generative learning of a real dataset. We call this type of generative model a neural...
A montage-agnostic cross-user encoder is carried to eleven transradial amputees on a protocol matched to its intact-limb training data, and the prediction pre-registered for this study, which extends the encoder's baseline-strength account with the premise that amputee EMG is less separable, holds true only after a few...
This article presents a mathematical model of the Motivated Emotional Mind cognitive architecture developed for embodied intelligent systems. Such a system learns to maintain its homeostasis through a generalized form of reinforcement learning based on its internal motivations, termed motivated learning (ML). The princ...
This study develops NeuroSketch, a practical design recipe for neural decoding, through a basic architecture study followed by macro- and micro-level optimization, and finds that CNN-2D outperforms other architectures in neural decoding tasks and explores its effectiveness from temporal and spatial perspectives.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
