Convolutional neural network

Predicting neural activity in higher visual areas (HVAs) in mice during spatial navigation is challenging due to the complex interaction between spatial and temporal processing. One recent two-stream hypothesis for rodents proposed by Saleem (2020) suggests that form-based goals and detailed landmark signals are processed by cortical areas biased towards the central visual field, while self-motion signals are processed in the periphery. Inspired by this, we developed a deep learning model that splits visual input into two streams: a convolutional neural network (CNN) processed the central visu

Motor brain-machine interfaces (BMIs) decode neural signals to help people with paralysis move and communicate. Even with important advances in the last two decades, BMIs face key obstacles to clinical viability. Invasive BMIs achieve proficient cursor and robotic arm control but require neurosurgery, posing significant risk to patients. Non-invasive BMIs do not have neurosurgical risk, but achieve lower performance, sometimes being prohibitively frustrating to use and preventing widespread adoption. We take a step toward breaking this performance-risk tradeoff by building performant non-invas

…to three predictions about the optimal neural response variability that minimizes generalization error: (i) the optimal variability m

Animals rely on sensory inputs to navigate complex, dynamic environments. Understanding how the brain integrates these inputs to guide behavior remains a central question in neuroscience. Training AI and animals on the same task offers a unique opportunity to uncover both similarities and critical differences in the strategies used by biological and artificial systems. By pinpointing what the brain accomplishes that modern AI lacks, we can drive advancements in machine learning, pushing AI to more robust, generalizable solutions. In this study, we train mice and reinforcement learning agents o

…from the hippocampus to neocortical networks. To understand the mechanisms governing SWRs, we have developed a closed-loop stimulation framework tailored for the real-time detection and suppression of SWRs, leveraging the ONIX electrophysiology acquisition system and BONSAI-RX acquisition software. As part of our Bonsai package, we developed a convolutional neural network (CNN) for detection of SWRs recorded with lam

Aims: Recent research showed that selective attention to speech can be decoded from non-invasive EEG recordings [1]. This effect could potentially be applied in neuro-steered CIs, which could aid the wearer in noisy environments. Here we examine linear and non-linear decoding methods for selective attention, specifically for bimodal CI users, in a competing speaker scenario.Methods: EEG data was collected from 23 bimodal CI patients exposed to two competing speech stimuli emanating from spatially separated speakers. Patients were directed to focus on one speech stream during a given segment. D

…Brain network dysfunctions are supported as a neurobiological basis for ASDs. Thus, functional connectivity (FC) studies are pivotal for unraveling autism-related large-scale network dynamics. Although functional imaging studies during development can be instrumental for autism diagnosis, longitudinal studies of FC consolidation over development to adulthood are missing in mice. SHANK3 is a postsynaptic scaffolding protein of excitatory synapses. Its deletion or mutation is

…from the hippocampus to neocortical networks. To understand the mechanisms governing SWRs, we have developed a closed-loop stimulation framework tailored for the real-time detection and suppression of SWRs, leveraging the ONIX electrophysiology acquisition system and BONSAI-RX acquisition software. As part of our Bonsai package, we developed a convolutional neural network (CNN) for detection of SWRs recorded with lam

…need, we developed a method based on a convolutional neural network (CNN) with specific enhancements which we apply to freely moving C. elegans. For a traditional CNN to track neurons across i

…Here, we trained a convolutional neural network model (CNN) on large-scale functional two-photon recordings of RGC responses to natural mouse movies, and the

Information retrieval from brain responses to auditory and visual stimuli has shown success through classification of song names and image classes presented to participants while recording EEG signals. Information retrieval in the form of reconstructing auditory stimuli has also shown some success, but here we improve on previous methods by reconstructing music stimuli well enough to be perceived and identified independently. Furthermore, deep learning models were trained on time-aligned music stimuli spectrum for each corresponding one-second window of EEG recording, which greatly reduces fea

While non-invasive Brain-to-Computer interface can accurately classify the lateralization of hand moments, the distinction of fingers activation in the same hand is limited by their local and overlapping representation in the motor cortex. In particular, the low signal-to-noise ratio restrains the opportunity to identify meaningful patterns in a supervised fashion. Here we combined Magnetoencephalography (MEG) recordings with advanced decoding strategy to classify finger movements at single trial level. We recorded eight subjects performing a serial reaction time task, where they pressed four

Neural representations of time are central to our understanding of the world around us. I review cognitive, neurophysiological and theoretical work that converges on three simple ideas. First, the time of past events is remembered via populations of neurons with a continuum of functional time constants. Second, these time constants evenly tile the log time axis. This results in a neural Weber-Fechner scale for time which can support behavioral Weber-Fechner laws and characteristic behavioral effects in memory experiments. Third, these populations appear as dual pairs---one type of population c

Understanding how sensory neurons extract relevant information from natural scenes is a major challenge in neuroscience. Probing sensory systems with simple stimuli give limited insights on natural scene processing, and probing selectivity during natural scene stimulation is difficult. Even in the retina, is not clear how Retinal ganglion cells (RGC) extract specific features from natural scenes and send this information to the brain. Many studies using simple, artificial stimuli have shown responses to local light increase (ON-responses), and/or decrease (OFF), but it is unclear if this selec

Mapping the spatial patterns of synaptic connectivity is essential for understanding neural circuit function. Two-photon optogenetics combined with whole-cell patch clamp enable synaptic circuit mapping in mammalian cortex. We consider an experimental set-up in which the experimenter patches a single target cell and uses two-photon optogenetics to stimulate surrounding tissue in a 3-dimensional grid while measuring postsynaptic currents (PSCs). This yields a high resolution spatial map of putative synaptic connections to a single neuron. However, these connectivity maps are noisy due to biolog

…Here, we introduce a 1D convolutional neural network (CNN) operating o