Related papers: Delving Deeper Into Astromorphic Transformers

Astrocytes are a ubiquitous and enigmatic type of non-neuronal cell and are found in the brain of all vertebrates. While traditionally viewed as being supportive of neurons, it is increasingly recognized that astrocytes may play a more…

While neuromorphic computing architectures based on Spiking Neural Networks (SNNs) are increasingly gaining interest as a pathway toward bio-plausible machine learning, attention is still focused on computational units like the neuron and…

The neuronal paradigm of studying the brain has left us with limitations in both our understanding of how neurons process information to achieve biological intelligence and how such knowledge may be translated into artificial intelligence…

Within the complex neuroarchitecture of the brain, astrocytes play crucial roles in development, structure, and metabolism. These cells regulate neural activity through tripartite synapses, directly impacting cognitive processes such as…

At tripartite synapses, astrocytes are in close contact with neurons and contribute to various functions, from synaptic transmission, maintenance of ion homeostasis and glutamate uptake to metabolism. However, disentangling the precise…

Traditional artificial neural networks take inspiration from biological networks, using layers of neuron-like nodes to pass information for processing. More realistic models include spiking in the neural network, capturing the electrical…

Astrocytes, the most abundant type of glial cell, play a fundamental role in memory. Despite most hippocampal synapses being contacted by an astrocyte, there are no current theories that explain how neurons, synapses, and astrocytes might…

A major goal of neuroscience is to understand brain computations during visual processing in naturalistic settings. A dominant approach is to use image-computable deep neural networks trained with different task objectives as a basis for…

Neuromorphic computing is emerging to be a disruptive computational paradigm that attempts to emulate various facets of the underlying structure and functionalities of the brain in the algorithm and hardware design of next-generation…

Understanding the role of astrocytes in brain computation is a nascent challenge, promising immense rewards, in terms of new neurobiological knowledge that can be translated into artificial intelligence. In our ongoing effort to identify…

Neuroscience has long informed the development of artificial neural networks, but the success of modern architectures invites, in turn, the converse: can modern networks teach us lessons about brain function? Here, we examine the structure…

Attending to what is relevant is fundamental to both the mammalian brain and modern machine learning models such as Transformers. Yet, determining relevance remains a core challenge, traditionally offloaded to learning algorithms like…

Deciphering the complex interactions between neurotransmission and astrocytic $Ca^{2+}$ elevations is a target promising a comprehensive understanding of brain function. While the astrocytic response to excitatory synaptic activity has been…

Artificial neural networks and computational neuroscience models have made tremendous progress, allowing computers to achieve impressive results in artificial intelligence (AI) applications, such as image recognition, natural language…

The self-attention mechanism, a cornerstone of Transformer-based state-of-the-art deep learning architectures, is largely heuristic-driven and fundamentally challenging to interpret. Establishing a robust theoretical foundation to explain…

Brain activities are featured by spatially distributed neural clusters of coherent firings and a spontaneous switching of the clusters between the synchrony and asynchrony states. Evidences from {\it in vivo} experiments suggest that…

Many deep neural network architectures loosely based on brain networks have recently been shown to replicate neural firing patterns observed in the brain. One of the most exciting and promising novel architectures, the Transformer neural…

We propose a design methodology to facilitate fault tolerance of deep learning models. First, we implement a many-core fault-tolerant neuromorphic hardware design, where neuron and synapse circuitries in each neuromorphic core are enclosed…

The different active roles of neurons and astrocytes during neuronal activation are associated with the metabolic processes necessary to supply the energy needed for their respective tasks at rest and during neuronal activation. Metabolism,…

This paper presents an innovative methodology for improving the robustness and computational efficiency of Spiking Neural Networks (SNNs), a critical component in neuromorphic computing. The proposed approach integrates astrocytes, a type…