The neurons of artificial neural networks were originally invented when much less was known about biological neurons than is known today. Our work explores a modification to the core neuron unit to make it more parallel to a biological neuron. The modification is made with the knowledge that biological dendrites are not simply passive activation funnels, but also compute complex non-linear functions as they transmit activation to the cell body. The paper explores a novel system of "Perforated" backpropagation empowering the artificial neurons of deep neural networks to achieve better performance coding for the same features they coded for in the original architecture. After an initial network training phase, additional "Dendrite Nodes" are added to the network and separately trained with a different objective: to correlate their output with the remaining error of the original neurons. The trained Dendrite Nodes are then frozen, and the original neurons are further trained, now taking into account the additional error signals provided by the Dendrite Nodes. The cycle of training the original neurons and then adding and training Dendrite Nodes can be repeated several times until satisfactory performance is achieved. Our algorithm was successfully added to modern state-of-the-art PyTorch networks across multiple domains, improving upon original accuracies and allowing for significant model compression without a loss in accuracy.

Enhancing the computational efficiency of on-device Deep Neural Networks (DNNs) remains a significant challengein mobile and edge computing. As we aim to execute increasingly complex tasks with constrained computational resources, much of the research has focused on compressing neural network structures and optimizing systems. Although many studies have focused on compressing neural network structures and parameters or optimizing underlying systems, there has been limited attention on optimizing the fundamental building blocks of neural networks: the neurons. In this study, we deliberate on a simple but important research question: Can we design artificial neurons that offer greater efficiency than the traditional neuron paradigm? Inspired by the threshold mechanisms and the excitation-inhibition balance observed in biological neurons, we propose a novel artificial neuron model, Threshold Neurons. Using Threshold Neurons, we can construct neural networks similar to those with traditional artificial neurons, while significantly reducing hardware implementation complexity. Our extensive experiments validate the effectiveness of neural networks utilizing Threshold Neurons, achieving substantial power savings of 7.51x to 8.19x and area savings of 3.89x to 4.33x at the kernel level, with minimal loss in precision. Furthermore, FPGA-based implementations of these networks demonstrate 2.52x power savings and 1.75x speed enhancements at the system level. The source code will be made available upon publication.

Graph-based representations for samples of computational mechanics-related datasets can prove instrumental when dealing with problems like irregular domains or molecular structures of materials, etc. To effectively analyze and process such datasets, deep learning offers Graph Neural Networks (GNNs) that utilize techniques like message-passing within their architecture. The issue, however, is that as the individual graph scales and/ or GNN architecture becomes increasingly complex, the increased energy budget of the overall deep learning model makes it unsustainable and restricts its applications in applications like edge computing. To overcome this, we propose in this paper Hybrid Variable Spiking Graph Neural Networks (HVS-GNNs) that utilize Variable Spiking Neurons (VSNs) within their architecture to promote sparse communication and hence reduce the overall energy budget. VSNs, while promoting sparse event-driven computations, also perform well for regression tasks, which are often encountered in computational mechanics applications and are the main target of this paper. Three examples dealing with prediction of mechanical properties of material based on microscale/ mesoscale structures are shown to test the performance of the proposed HVS-GNNs in regression tasks. We have also compared the performance of HVS-GNN architectures with the performance of vanilla GNNs and GNNs utilizing leaky integrate and fire neurons. The results produced show that HVS-GNNs perform well for regression tasks, all while promoting sparse communication and, hence, energy efficiency.

The human brain has long inspired the pursuit of artificial intelligence (AI). Recently, neuroimaging studies provide compelling evidence of alignment between the computational representation of artificial neural networks (ANNs) and the neural responses of the human brain to stimuli, suggesting that ANNs may employ brain-like information processing strategies. While such alignment has been observed across sensory modalities--visual, auditory, and linguistic--much of the focus has been on the behaviors of artificial neurons (ANs) at the population level, leaving the functional organization of individual ANs that facilitates such brain-like processes largely unexplored. In this study, we bridge this gap by directly coupling sub-groups of artificial neurons with functional brain networks (FBNs), the foundational organizational structure of the human brain. Specifically, we extract representative patterns from temporal responses of ANs in large language models (LLMs), and use them as fixed regressors to construct voxel-wise encoding models to predict brain activity recorded by functional magnetic resonance imaging (fMRI). This framework links the AN sub-groups to FBNs, enabling the delineation of brain-like functional organization within LLMs. Our findings reveal that LLMs (BERT and Llama 1-3) exhibit brain-like functional architecture, with sub-groups of artificial neurons mirroring the organizational patterns of well-established FBNs. Notably, the brain-like functional organization of LLMs evolves with the increased sophistication and capability, achieving an improved balance between the diversity of computational behaviors and the consistency of functional specializations. This research represents the first exploration of brain-like functional organization within LLMs, offering novel insights to inform the development of artificial general intelligence (AGI) with human brain principles.

The algorithms that underpin artificial intelligence systems like ChatGPT can't learn as they go along, forcing tech companies to spend billions of dollars to train new models from scratch. While this has been a concern in the industry for some time, a new study suggests there is an inherent problem with the way models are designed – but there may be a way to solve it. Most AIs today are so-called neural networks inspired by how brains work, with processing units known as artificial neurons. They typically go through distinct phases in their development. First, the AI is trained, which sees its artificial neurons fine-tuned by an algorithm to better reflect a given dataset.

For the past decade, AI researcher Chris Olah has been obsessed with artificial neural networks. One question in particular engaged him, and has been the center of his work, first at Google Brain, then OpenAI, and today at AI startup Anthropic, where he is a cofounder. "What's going on inside of them?" he says. "We have these systems, we don't know what's going on. That question has become a core concern now that generative AI has become ubiquitous. Large language models like ChatGPT, Gemini, and Anthropic's own Claude have dazzled people with their language prowess and infuriated people with their tendency to make things up. Their potential to solve previously intractable problems enchants techno-optimists. But LLMs are strangers in our midst. Even the people who build them don't know exactly how they work, and massive effort is required to create guardrails to prevent them from churning out bias, misinformation, and even blueprints for deadly chemical weapons. If the people building the models knew what happened inside these "black boxes,'' it would be easier to make them safer.

Intel has created the world's largest neuromorphic computer, a device intended to mimic the operation of the human brain. The firm hopes that it will be able to run more sophisticated AI models than is possible on conventional computers, but experts say there are engineering hurdles to overcome before the device can compete with the state of the art, let alone exceed it. Expectations for neuromorphic computers are high because they are inherently different to traditional machines. While a regular computer uses its processor to carry out operations and stores data in separate memory, a neuromorphic device uses artificial neurons to both store and compute, just as our brains do. This removes the need to shuttle data back and forth between components, which can be a bottleneck for current computers.

We propose, in this paper, a Variable Spiking Wavelet Neural Operator (VS-WNO), which aims to bridge the gap between theoretical and practical implementation of Artificial Intelligence (AI) algorithms for mechanics applications. With recent developments like the introduction of neural operators, AI's potential for being used in mechanics applications has increased significantly. However, AI's immense energy and resource requirements are a hurdle in its practical field use case. The proposed VS-WNO is based on the principles of spiking neural networks, which have shown promise in reducing the energy requirements of the neural networks. This makes possible the use of such algorithms in edge computing. The proposed VS-WNO utilizes variable spiking neurons, which promote sparse communication, thus conserving energy, and its use is further supported by its ability to tackle regression tasks, often faced in the field of mechanics. Various examples dealing with partial differential equations, like Burger's equation, Allen Cahn's equation, and Darcy's equation, have been shown. Comparisons have been shown against wavelet neural operator utilizing leaky integrate and fire neurons (direct and encoded inputs) and vanilla wavelet neural operator utilizing artificial neurons. The results produced illustrate the ability of the proposed VS-WNO to converge to ground truth while promoting sparse communication.

With their recent development, large language models (LLMs) have been found to exhibit a certain level of Theory of Mind (ToM), a complex cognitive capacity that is related to our conscious mind and that allows us to infer another's beliefs and perspective. While human ToM capabilities are believed to derive from the neural activity of a broadly interconnected brain network, including that of dorsal medial prefrontal cortex (dmPFC) neurons, the precise processes underlying LLM's capacity for ToM or their similarities with that of humans remains largely unknown. In this study, we drew inspiration from the dmPFC neurons subserving human ToM and employed a similar methodology to examine whether LLMs exhibit comparable characteristics. Surprisingly, our analysis revealed a striking resemblance between the two, as hidden embeddings (artificial neurons) within LLMs started to exhibit significant responsiveness to either true- or false-belief trials, suggesting their ability to represent another's perspective. These artificial embedding responses were closely correlated with the LLMs' performance during the ToM tasks, a property that was dependent on the size of the models. Further, the other's beliefs could be accurately decoded using the entire embeddings, indicating the presence of the embeddings' ToM capability at the population level. Together, our findings revealed an emergent property of LLMs' embeddings that modified their activities in response to ToM features, offering initial evidence of a parallel between the artificial model and neurons in the human brain.

Understanding how language supports emotion inference remains a topic of debate in emotion science. The present study investigated whether language-derived emotion-concept knowledge would causally support emotion inference by manipulating the language-specific knowledge representations in large language models. Using the prompt technique, 14 attributes of emotion concepts were found to be represented by distinct artificial neuron populations. By manipulating these attribute-related neurons, the majority of the emotion inference tasks showed performance deterioration compared to random manipulations. The attribute-specific performance deterioration was related to the importance of different attributes in human mental space. Our findings provide causal evidence in support of a language-based mechanism for emotion inference and highlight the contributions of emotion-concept knowledge.