Related papers: On-chip Few-shot Learning with Surrogate Gradient …
Spintronic nano-neurons offer a promising route towards energy-efficient, high-performance hardware neural networks thanks to their inherent low-input nonlinear dynamics. However, training such networks remains a major bottleneck as it…
As the technology industry is moving towards implementing tasks such as natural language processing, path planning, image classification, and more on smaller edge computing devices, the demand for more efficient implementations of…
Despite the promise of superior efficiency and scalability, real-world deployment of emerging nanoelectronic platforms for brain-inspired computing have been limited thus far, primarily because of inter-device variations and intrinsic…
We propose to study the problem of few-shot learning with the prism of inference on a partially observed graphical model, constructed from a collection of input images whose label can be either observed or not. By assimilating generic…
After several decades of continuously optimizing computing systems, the Moore's law is reaching itsend. However, there is an increasing demand for fast and efficient processing systems that can handlelarge streams of data while decreasing…
Few-shot learning aims to recognize new categories using very few labeled samples. Although few-shot learning has witnessed promising development in recent years, most existing methods adopt an average operation to calculate prototypes,…
Adaptive "life-long" learning at the edge and during online task performance is an aspirational goal of AI research. Neuromorphic hardware implementing Spiking Neural Networks (SNNs) are particularly attractive in this regard, as their…
Few-shot learning is a technique to learn a model with a very small amount of labeled training data by transferring knowledge from relevant tasks. In this paper, we propose a few-shot learning method for wearable sensor based human activity…
As robots become smarter and more ubiquitous, optimizing the power consumption of intelligent compute becomes imperative towards ensuring the sustainability of technological advancements. Neuromorphic computing hardware makes use of…
Physical neuromorphic computing, exploiting the complex dynamics of physical systems, has seen rapid advancements in sophistication and performance. Physical reservoir computing, a subset of neuromorphic computing, faces limitations due to…
The goal of few-shot learning is to generalize and achieve high performance on new unseen learning tasks, where each task has only a limited number of examples available. Gradient-based meta-learning attempts to address this challenging…
Neuromorphic computing aims to replicate the brain's capabilities for energy efficient and parallel information processing, promising a solution to the increasing demand for faster and more efficient computational systems. Efficient…
Gradient-based meta-learning techniques are both widely applicable and proficient at solving challenging few-shot learning and fast adaptation problems. However, they have practical difficulties when operating on high-dimensional parameter…
We explore three representative lines of research and demonstrate the utility of our methods on a classification benchmark of brain cancer MRI data. First, we present a capsule network that explicitly learns a representation robust to…
Recent years have witnessed the great progress of deep neural networks on semantic segmentation, particularly in medical imaging. Nevertheless, training high-performing models require large amounts of pixel-level ground truth masks, which…
In task-based few-shot learning paradigms, it is commonly assumed that different tasks are independently and identically distributed (i.i.d.). However, in real-world scenarios, the distribution encountered in few-shot learning can…
Backpropagation algorithms on recurrent artificial neural networks require an unfolding of accumulated states over time. These states must be kept in memory for an undefined period of time which is task-dependent. This paper uses the…
Domain-specialized FPGAs have delivered unprecedented performance for low-latency inference across scientific and industrial workloads, yet nearly all existing accelerators assume static models trained offline, relegating learning and…
Objective: This work explores use of a few-shot transfer learning method to train and implement a convolutional spiking neural network (CSNN) on a BrainChip Akida AKD1000 neuromorphic system-on-chip for developing individual-level, instead…
The highly sparse activations in Spiking Neural Networks (SNNs) can provide tremendous energy efficiency benefits when carefully exploited in hardware. The behavior of sparsity in SNNs is uniquely shaped by the dataset and training…