https://neurosciencenews.com/neuroscience-topics/deep-learning/ Neuroscience News provides research news for neuroscience, neurology, psychology, AI, brain science, mental health, robotics and cognitive sciences. Tue, 10 Mar 2026 17:36:14 +0000 en-US hourly 1 https://wordpress.org/?v=6.9.4 https://neurosciencenews.com/files/2020/08/cropped-Neuroscience-News-Site-Icon-512-comp-32x32.jpg https://neurosciencenews.com/neuroscience-topics/deep-learning/ 32 32 66008408 https://neurosciencenews.com/ai-genetics-language-neuroscience-30283/ https://neurosciencenews.com/ai-genetics-language-neuroscience-30283/#respond Tue, 10 Mar 2026 17:36:11 +0000 https://neurosciencenews.com/?p=115323 From AI-driven brain models to the shared genetics of music and reading, scientists are finally decoding the brain's most complex system.]]> https://neurosciencenews.com/ai-genetics-language-neuroscience-30283/feed/ 0 115323 https://neurosciencenews.com/navigation-brain-structure-ai-30228/ https://neurosciencenews.com/navigation-brain-structure-ai-30228/#respond Mon, 02 Mar 2026 21:33:14 +0000 https://neurosciencenews.com/?p=115124 Advanced AI tools fail to find a link between the physical structure of the brain and navigation ability, challenging decades of neuroscientific assumptions.]]> https://neurosciencenews.com/navigation-brain-structure-ai-30228/feed/ 0 115124 https://neurosciencenews.com/ai-animal-behavior-30091/ https://neurosciencenews.com/ai-animal-behavior-30091/#comments Wed, 11 Feb 2026 23:21:53 +0000 https://neurosciencenews.com/?p=114552 Researchers developed an advanced AI system named YORU that can identify specific animal behaviors with over 90% accuracy across multiple species. By combining this high-speed recognition with optogenetics, the team successfully demonstrated the ability to shut down specific brain circuits in real-time using targeted light.]]> https://neurosciencenews.com/ai-animal-behavior-30091/feed/ 3 114552 https://neurosciencenews.com/ai-brain-neuron-learning-30073/ https://neurosciencenews.com/ai-brain-neuron-learning-30073/#comments Mon, 29 Dec 2025 17:42:19 +0000 https://neurosciencenews.com/?p=114459 A biologically grounded computational model built to mimic real neural circuits, not trained on animal data, learned a visual categorization task just as actual lab animals do, matching their accuracy, variability, and underlying neural rhythms. By integrating fine-scale synaptic rules with large-scale architecture across cortex, striatum, brainstem, and acetylcholine-modulated systems, the model reproduced hallmark patterns of learning, including strengthened beta-band synchrony between regions during correct decisions.]]> https://neurosciencenews.com/ai-brain-neuron-learning-30073/feed/ 1 114459 https://neurosciencenews.com/consciousness-computing-ai-30068/ https://neurosciencenews.com/consciousness-computing-ai-30068/#comments Tue, 23 Dec 2025 18:01:36 +0000 https://neurosciencenews.com/?p=114438 A new theoretical framework argues that the long-standing split between computational functionalism and biological naturalism misses how real brains actually compute. The authors propose “biological computationalism,” the idea that neural computation is inseparable from the brain’s physical, hybrid, and energy-constrained dynamics rather than an abstract algorithm running on hardware. In this view, discrete neural events and continuous physical processes form a tightly coupled system that cannot be reduced to symbolic information processing. ]]> https://neurosciencenews.com/consciousness-computing-ai-30068/feed/ 2 114438 https://neurosciencenews.com/ai-brain-fear-30044/ Fri, 12 Dec 2025 18:54:57 +0000 https://neurosciencenews.com/?p=114346 Researchers have developed an AI-driven brain model that can track fear as it unfolds in real-world situations, offering a major shift from traditional lab-based approaches. Classic fear studies often rely on static images, but these do not reflect how the brain processes fear in dynamic contexts. ]]> 114346 https://neurosciencenews.com/ai-dementia-detector-neurotech-30037/ Wed, 10 Dec 2025 20:57:33 +0000 https://neurosciencenews.com/?p=114322 New research shows that deep learning can use EEG signals to distinguish Alzheimer’s disease from frontotemporal dementia with high accuracy. By analyzing both the timing and frequency of brain activity, the model uncovered distinct patterns: broader disruption across multiple regions in Alzheimer’s and more localized frontal and temporal changes in frontotemporal dementia. ]]> 114322 https://neurosciencenews.com/ai-bionic-hand-30031/ Tue, 09 Dec 2025 20:26:46 +0000 https://neurosciencenews.com/?p=114301 A new study shows that integrating artificial intelligence with advanced proximity and pressure sensors allows a commercial bionic hand to grasp objects in a natural, intuitive way—reducing cognitive effort for amputees. By training an artificial neural network on grasping postures, each finger could independently “see” objects and automatically move into the correct position, improving grip security and precision. ]]> 114301 https://neurosciencenews.com/ai-language-brain-30025/ Mon, 08 Dec 2025 17:31:14 +0000 https://neurosciencenews.com/?p=114276 The human brain processes spoken language in a step-by-step sequence that closely matches how large language models transform text. Using electrocorticography recordings from people listening to a podcast, researchers found that early brain responses aligned with early AI layers, while deeper layers corresponded to later neural activity in regions such as Broca’s area. ]]> 114276 https://neurosciencenews.com/ai-grief-death-30009/ Wed, 03 Dec 2025 17:42:26 +0000 https://neurosciencenews.com/?p=114211 Generative artificial intelligence is quietly reshaping how humans process grief, remembrance, and mortality. Digital reconstructions of the deceased may offer comfort, but they also risk blurring the natural boundary between presence and absence. ]]> 114211 https://neurosciencenews.com/ai-painist-muscle-movement-29998/ Mon, 01 Dec 2025 20:12:54 +0000 https://neurosciencenews.com/?p=114169 Researchers developed an AI system that can reconstruct fine hand muscle activity using only standard video footage. Traditionally, this type of measurement required intrusive electrodes attached to the skin, but the new method eliminates that need entirely. ]]> 114169 https://neurosciencenews.com/ai-strss-body-29987/ Wed, 26 Nov 2025 20:06:33 +0000 https://neurosciencenews.com/?p=114122 Researchers developed an AI tool that detects chronic stress by measuring adrenal gland volume on routine chest CT scans. This biomarker aligns with cortisol levels, stress questionnaires, and future cardiovascular outcomes, offering the first imaging-based method to quantify stress load in the body.]]> 114122