Related papers: Nengo and low-power AI hardware for robust, embedd…
Spiking neural networks (SNNs) have been recently brought to light due to their promising capabilities. SNNs simulate the brain with higher biological plausibility compared to previous generations of neural networks. Learning with fewer…
Computational experiments are exploited in finding a well-designed processing path to optimize material structures for desired properties. This requires understanding the interplay between the processing-(micro)structure-property linkages…
The synergy between spiking neural networks and neuromorphic hardware holds promise for the development of energy-efficient AI applications. Inspired by this potential, we revisit the foundational aspects to study the capabilities of…
It has long been realized that neuromorphic hardware offers benefits for the domain of robotics such as low energy, low latency, as well as unique methods of learning. In aiming for more complex tasks, especially those incorporating…
Neuromorphic hardware platforms can significantly lower the energy overhead of a machine learning inference task. We present a design-technology tradeoff analysis to implement such inference tasks on the processing elements (PEs) of a Non-…
The growing need for intelligent, adaptive, and energy-efficient autonomous systems across fields such as robotics, mobile agents (e.g., UAVs), and self-driving vehicles is driving interest in neuromorphic computing. By drawing inspiration…
Concept learning deals with learning description logic concepts from a background knowledge and input examples. The goal is to learn a concept that covers all positive examples, while not covering any negative examples. This non-trivial…
Despite the growing interest in robot control utilizing the computation of biological neurons, context-dependent behavior by neuron-connected robots remains a challenge. Context-dependent behavior here is defined as behavior that is not the…
Energy efficiency and low latency are crucial requirements for designing wearable AI-empowered human activity recognition systems, due to the hard constraints of battery operations and closed-loop feedback. While neural network models have…
Robust fitting of geometric models is a fundamental task in many computer vision pipelines. Numerous innovations have been produced on the topic, from improving the efficiency and accuracy of random sampling heuristics to generating novel…
We present an exploration of machine learning architectures for predicting brain responses to realistic images on occasion of the Algonauts Challenge 2023. Our research involved extensive experimentation with various pretrained models.…
As robots increasingly coexist with humans, they must navigate complex, dynamic environments rich in visual information and implicit social dynamics, like when to yield or move through crowds. Addressing these challenges requires…
Emerging two terminal nanoscale memory devices, known as memristors, have over the past decade demonstrated great potential for implementing energy efficient neuro-inspired computing architectures. As a result, a wide-range of technologies…
The practical applications based on recurrent spiking neurons are limited due to their non-trivial learning algorithms. The temporal nature of spiking neurons is more favorable for hardware implementation where signals can be represented in…
Models with fewer parameters are necessary for the neural control of memory-limited, performant robots. Finding these smaller neural network architectures can be time-consuming. We propose HyperPPO, an on-policy reinforcement learning…
As humans advance toward a higher level of artificial intelligence, it is always at the cost of escalating computational resource consumption, which requires developing novel solutions to meet the exponential growth of AI computing demand.…
Spiking Neural Networks (SNNs) have the potential to drastically reduce the energy requirements of AI systems. However, mainstream accelerators like GPUs and TPUs are designed for the high arithmetic intensity of standard ANNs so are not…
Resistive memory (RM) based neuromorphic systems can emulate synaptic plasticity and thus support continual learning, but they generally lack biologically inspired mechanisms for active forgetting, which are critical for meeting modern data…
The remarkable advancements in artificial intelligence (AI), primarily driven by deep neural networks, are facing challenges surrounding unsustainable computational trajectories, limited robustness, and a lack of explainability. To develop…
The emergence of heterogeneity and domain-specific architectures targeting deep learning inference show great potential for enabling the deployment of modern CNNs on resource-constrained embedded platforms. A significant development is the…