Self-supervised learning

Much is known about the neural representations of current environmental location and direction within the hippocampal formation, but use of such a “cognitive map” requires the online representation of desired locations and how to get there, and the neural basis for this function has been more elusive. I will discuss how “theta sweeps” of place and grid cell firing encode the current location (at early phases of each theta cycle) while, at later phases, sampling around the forward direction during exploration and indicating the direction to desired locations during goal-directed navigation. I w

…Recent approaches in representation learning circumvent the need for labeled examples, and match or surpass supervised learning methods on a variety of tasks. These approaches generally rely on supervision signals extracted from the

…Recent advances in self-supervised learning now allow for modeling both modalities jointly. In this work, we introduce a multimodal masked modeling approach that masks portions of both behavior and neural activity, using the unmasked data to make predictions across both modalities. We evaluat

…to aid in the design of artificial learning systems, and help reveal how neurodevelopmental disorders alter information processing. Here we examine the developmental changes in signal and noise correlation structure of neural activity by analyzing neural recordings of the zebrafish optic tectum evoked by prey-like visual stimuli. We found that si

Automated axon tracing via fully supervised learning requires annotated 3D brain imagery, which necessitates expertise and labor to produce. Reducing the amount of annotated training data needed for supervised algorithms for axon tracing would expedite critical brain research. In this work, we developed and integrated a self-supervised learning (SSL) algorithm trained on large unannotated data volumes into NeuroTrALE (pictured), a custom AI-driven pipeline for automatic annotation and visualization of 3D brain imagery. Our light sheet microscopy dataset consisted of stained Parvalbumin positiv

…Our goal is to develop a self-supervised learning method for optimal detection of such motifs in neurobiological data.To detect such motifs, we have extended the K-Means algorithm to process temporal data using a convolutional operator. A second pooling layer ensures that only one motif is used per time step. The results were improved by ensuring that the detected motifs are equiprobably activated

…for individualized representation learning of rs-fMRI. The system includes a “deep” base with “shallow” adds-on. The “deep” base is trained through multiple stages of self-supervised learning with unlabeled rs-fMRI. After the base is trained and fixed, the “shallow” adds-on are trained with supervised learning for behavior prediction. The base includes a variational auto-encoder (VAE) for unsupervised learning of spatial representations, a Bi-d

Biological visual systems have evolved around the efficient coding of natural image statistics in order to support recognition of complex visual patterns. Recent work has shown that deep neural networks are able to learn similar representations to those measured in visual areas in animals, suggesting they may serve as models for the brain. Varying network architectures and loss functions has been shown to modulate the biological similarity learned representations, however the extent to which this results from exposure to natural image statistics during training has not been fully characterized

Animals exhibit remarkable learning capabilities with little direct supervision. Likewise, self-supervised learning is an emergent paradigm in artificial intelligence, closing the performance gap to supervised learning. In the context of biology, self-supervised learning corresponds to a setting where one sense or specific stimulus may serve as a supervisory signal for another. After learning, the latter can be used to predict the former. On the implementation level, it has been demonstrated that such predictive learning can occur at the single neuron level, in compartmentalized neurons that s

Learning in the brain is thought to be largely unsupervised since the bulk of an animal’s natural experience arrives neither with associated reinforcement signals nor explicit supervisory signals. A compelling account of unsupervised learning in animals is provided by the notion that the brain learns by trying to predict the future, thereby identifying statistical redundancies in sensory inputs over time. Based on this principle, self-supervised learning (SSL) techniques have enabled deep artificial neural networks (ANNs) to achieve competitive results on challenging perceptual tasks. SSL atte

…we hypothesize that a key part of this learning ability is the use of self-generated navigational information as a similarity label to drive a learning objective for self-supervised learning. The goal of this work is to exploit navigational information in a visual environment to provide performance in training that exceeds the state-of-the-art self-supervised training. Here, we show that using spatial and temporal information in the pretraining stage of contrastive learning can improve the performan