Related papers: Online Few-shot Gesture Learning on a Neuromorphic…
Segmenting and recognizing surgical operation trajectories into distinct, meaningful gestures is a critical preliminary step in surgical workflow analysis for robot-assisted surgery. This step is necessary for facilitating learning from…
Photonic technologies hold significant potential for creating innovative, high-speed, efficient and hardware-friendly neuromorphic computing platforms. Neuromorphic photonic methods leveraging ubiquitous, technologically mature and…
Spiking neural networks (SNNs) are a bio-inspired alternative to conventional real-valued deep learning models, with the potential for substantially higher energy efficiency. Interest in SNNs has recently exploded due to a major…
Achieving optimal semantic segmentation with frame-based vision sensors poses significant challenges for real-time systems like UAVs and self-driving cars, which require rapid and precise processing. Traditional frame-based methods often…
One-shot Imitation Learning~(OSIL) aims to imbue AI agents with the ability to learn a new task from a single demonstration. To supervise the learning, OSIL typically requires a prohibitively large number of paired expert demonstrations --…
Recent advances in memory technologies, devices and materials have shown great potential for integration into neuromorphic electronic systems. However, a significant gap remains between the development of these materials and the realization…
Tracking visual objects from a single initial exemplar in the testing phase has been broadly cast as a one-/few-shot problem, i.e., one-shot learning for initial adaptation and few-shot learning for online adaptation. The recent few-shot…
Spiking Neural Networks (SNNs) offer a promising alternative to conventional Artificial Neural Networks (ANNs) for the implementation of on-device low-power online learning and inference. On-device training is, however, constrained by the…
We present a neuromorphic radar framework for real-time, low-power hand gesture recognition (HGR) using an event-driven architecture inspired by biological sensing. Our system comprises a 24 GHz Doppler radar front-end and a custom…
Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points, without forgetting knowledge of old classes. The difficulty lies in that limited data…
Few-shot learning (FSL) techniques seek to learn the underlying patterns in data using fewer samples, analogous to how humans learn from limited experience. In this limited-data scenario, the challenges associated with deep neural networks,…
For Edge AI applications, deploying online learning and adaptation on resource-constrained embedded devices can deal with fast sensor-generated streams of data in changing environments. However, since maintaining low-latency and…
AI systems on edge devices require online continual learning -- adapting to non-stationary streams and unfamiliar classes without catastrophic forgetting -- under strict power constraints. We present CLP-SNN, a spiking neural network with a…
Brain-computer interfaces are being explored for a wide variety of therapeutic applications. Typically, this involves measuring and analyzing continuous-time electrical brain activity via techniques such as electrocorticogram (ECoG) or…
The rising demand for energy-efficient edge AI systems (e.g., mobile agents/robots) has increased the interest in neuromorphic computing, since it offers ultra-low power/energy AI computation through spiking neural network (SNN) algorithms…
Neuromorphic image sensors produce activity-driven spiking output at every pixel. These low-power consuming imagers which encode visual change information in the form of spikes help reduce computational overhead and realize complex…
As intelligent systems become increasingly important in our daily lives, new ways of interaction are needed. Classical user interfaces pose issues for the physically impaired and are partially not practical or convenient. Gesture…
The human brain is a complex spiking neural network (SNN), capable of learning multimodal signals in a zero-shot manner by generalizing existing knowledge. Remarkably, it maintains minimal power consumption through event-based signal…
Neuromorphic computing is an emerging computing paradigm that moves away from batched processing towards the online, event-driven, processing of streaming data. Neuromorphic chips, when coupled with spike-based sensors, can inherently adapt…
Configurable synaptic delays are a basic feature in many neuromorphic neural network hardware accelerators. However, they have been rarely used in model implementations, despite their promising impact on performance and efficiency in tasks…