A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Gradient model for memristive systems in neurophysiology and neuromorphic circuits.
New method uses surrogate gradients to train efficient spiking networks on neuromorphic hardware.
Neuromorphic Computing is a nascent research field in which models and devices are designed to process information by emulating biological neural systems. Thanks to their superior energy efficiency, analog neuromorphic systems are highly promising for embedded, wearable, and implantable systems. However, optimizing neu…
Paper reviews neuromorphic engineering features and compares analog vs digital systems.
A learning rule for first-spike times in neural networks reduces energy consumption and reaction times.
A brain-inspired spiking Transformer reduces energy consumption and enhances interpretability.
SNNs optimize cross-market portfolios with neuromorphic computing, reducing computational overhead and improving returns.
Improves energy efficiency of neuromorphic hardware by optimizing memory organization and encoding schemes.
Despite being originally inspired by the central nervous system, artificial neural networks have diverged from their biological archetypes as they have been remodeled to fit particular tasks. In this paper, we review several possibilites to reverse map these architectures to biologically more realistic spiking networks…
How spiking networks are able to perform probabilistic inference is an intriguing question, not only for understanding information processing in the brain, but also for transferring these computational principles to neuromorphic silicon circuits. A number of computationally powerful spiking network models have been pro…
ConformalHDC improves HDC's uncertainty quantification for neuromorphic learning.
Neuromorphic column performs online unsupervised clustering.
Low precision networks in the reinforcement learning (RL) setting are relatively unexplored because of the limitations of binary activations for function approximation. Here, in the discrete action ATARI domain, we demonstrate, for the first time, that low precision policy distillation from a high precision network pro…
High-speed model accurately simulates neuromorphic devices.
VOWEL trains WTA-SNNs for multi-valued events, overcoming resource limitations.
The paper introduces reservoir computing models for complex systems.
New framework boosts neural network performance and resilience.
Python scripts analyze MRAM-based neuromorphic devices' process variation impacts on machine learning accuracy.
Sleep-based regularization stabilizes STDP in recurrent neural networks.
Using Intel's Loihi neuromorphic research chip and ABR's Nengo Deep Learning toolkit, we analyze the inference speed, dynamic power consumption, and energy cost per inference of a two-layer neural network keyword spotter trained to recognize a single phrase. We perform comparative analyses of this keyword spotter runni…
Enhances SNNs for spatio-temporal feature extraction.
Neuromorphic hardware platforms, such as Intel's Loihi chip, support the implementation of Spiking Neural Networks (SNNs) as an energy-efficient alternative to Artificial Neural Networks (ANNs). SNNs are networks of neurons with internal analogue dynamics that communicate by means of binary time series. In this work, a…
New algorithm learns uncertainty for edge devices.
Bio-inspired neuromorphic hardware is a research direction to approach brain's computational power and energy efficiency. Spiking neural networks (SNN) encode information as sparsely distributed spike trains and employ spike-timing-dependent plasticity (STDP) mechanism for learning. Existing hardware implementations of…
We study two aspects of noisy computations during inference. The first aspect is how to mitigate their side effects for naturally trained deep learning systems. One of the motivations for looking into this problem is to reduce the high power cost of conventional computing of neural networks through the use of analog ne…
An online algorithm improves cPCA for efficient, interpretable data analysis.
Fault-tolerant neural networks inspired by biological error correction codes.
PredPCA extracts key components for better time series prediction.
Efficient SNN on Loihi achieves high gesture recognition accuracy.
A new scheme reduces global search cost by a square root factor.
Information in neural networks is represented as weighted connections, or synapses, between neurons. This poses a problem as the primary computational bottleneck for neural networks is the vector-matrix multiply when inputs are multiplied by the neural network weights. Conventional processing architectures are not well…
The ability to learn and adapt in real time is a central feature of biological systems. Neuromorphic architectures demonstrating such versatility can greatly enhance our ability to efficiently process information at the edge. A key challenge, however, is to understand which learning rules are best suited for specific t…
SNNs can represent complex functions efficiently.
The paper relaxes constraints on predictive coding models, making them more biologically plausible.
Probabilistic topic models are popular unsupervised learning methods, including probabilistic latent semantic indexing (pLSI) and latent Dirichlet allocation (LDA). By now, their training is implemented on general purpose computers (GPCs), which are flexible in programming but energy-consuming. Towards low-energy imple…
A new hierarchy quantifies agency in systems based on information processing.
This work tackles catastrophic forgetting in neural networks by mimicking brain's metaplasticity.
We explore the robustness of recurrent neural networks when the computations within the network are noisy. One of the motivations for looking into this problem is to reduce the high power cost of conventional computing of neural network operations through the use of analog neuromorphic circuits. Traditional GPU/CPU-cen…
Spiking neural networks (SNNs) offer a promising alternative to current artificial neural networks to enable low-power event-driven neuromorphic hardware. Spike-based neuromorphic applications require processing and extracting meaningful information from spatio-temporal data, represented as series of spike trains over …
Meta-learning helps models learn quickly from few samples.
New method converts ANN gates to SNNs with AMOS neurons for improved image classification.
In this paper, a spintronic neuromorphic reconfigurable Array (SNRA) is developed to fuse together power-efficient probabilistic and in-field programmable deterministic computing during both training and evaluation phases of restricted Boltzmann machines (RBMs). First, probabilistic spin logic devices are used to devel…
This paper introduces a new learning rule for probabilistic SNNs that improves log-likelihood, accuracy, and calibration.
CoNNTrA trains DNNs with low-power, low-memory constraints.
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 limited amount of data available at each device. In this paper, we propose to mit…
Neuromorphic hardware tends to pose limits on the connectivity of deep networks that one can run on them. But also generic hardware and software implementations of deep learning run more efficiently for sparse networks. Several methods exist for pruning connections of a neural network after it was trained without conne…
We describe a new technique which minimizes the amount of neurons in the hidden layer of a random recurrent neural network (rRNN) for time series prediction. Merging Takens-based attractor reconstruction methods with machine learning, we identify a mechanism for feature extraction that can be leveraged to lower the net…
We propose reinforcement learning on simple networks consisting of random connections of spiking neurons (both recurrent and feed-forward) that can learn complex tasks with very little trainable parameters. Such sparse and randomly interconnected recurrent spiking networks exhibit highly non-linear dynamics that transf…