Related papers: Hierarchical Neural Memory Network for Low Latency…
We introduce and detail an atypical neural network architecture, called time elastic neural network (teNN), for multivariate time series classification. The novelty compared to classical neural network architecture is that it explicitly…
Hierarchical structures exist in both linguistics and Natural Language Processing (NLP) tasks. How to design RNNs to learn hierarchical representations of natural languages remains a long-standing challenge. In this paper, we define two…
Spatiotemporal information is at the core of diverse sensory processing and computational tasks. Feed-forward spiking neural networks can be used to solve these tasks while offering potential benefits in terms of energy efficiency by…
A biomimetic machine intelligence algorithm, that holds promise in creating invariant representations of spatiotemporal input streams is the hierarchical temporal memory (HTM). This unsupervised online algorithm has been demonstrated on…
Inference in deep neural networks can be computationally expensive, and networks capable of anytime inference are important in mscenarios where the amount of compute or quantity of input data varies over time. In such networks the inference…
Time series anomaly detection is critical for maintaining the reliability of mission-critical systems. While Transformer-based models like PatchTST have shown remarkable performance, their $\mathcal{O}(L^2)$ computational complexity…
Event-based vision sensors encode local pixel-wise brightness changes in streams of events rather than image frames and yield sparse, energy-efficient encodings of scenes, in addition to low latency, high dynamic range, and lack of motion…
Deep-learning based noise reduction algorithms have proven their success especially for non-stationary noises, which makes it desirable to also use them for embedded devices like hearing aids (HAs). This, however, is currently not possible…
Sensing is a universal task in science and engineering. Downstream tasks from sensing include inferring full state estimates of a system (system identification), control decisions, and forecasting. These tasks are exceptionally challenging…
We present a framework for modeling multi-scale processes, and study its performance in the context of streamflow forecasting in hydrology. Specifically, we propose a novel hierarchical recurrent neural architecture that factorizes the…
This paper introduces an unsupervised compact architecture that can extract features and classify the contents of dynamic scenes from the temporal output of a neuromorphic asynchronous event-based camera. Event-based cameras are clock-less…
It has been proposed that, when processing a stream of events, humans divide their experiences in terms of inferred latent causes (LCs) to support context-dependent learning. However, when shared structure is present across contexts, it is…
Real-world sequential signals, such as audio or video, contain critical information that is often embedded within long periods of silence or noise. While recurrent neural networks (RNNs) are designed to process such data efficiently, they…
Graph-based next-step prediction models have recently been very successful in modeling complex high-dimensional physical systems on irregular meshes. However, due to their short temporal attention span, these models suffer from error…
The ability to learn continuously from an incoming data stream without catastrophic forgetting is critical for designing intelligent systems. Many existing approaches to continual learning rely on stochastic gradient descent and its…
Industrial systems increasingly depend on Machine Learning (ML), and operate on heterogeneous nodes that must satisfy tight latency, energy, and memory constraints. Dynamic ML models, which reconfigure their computational footprint at…
We seek to enable classic processing of continuous ultra-sparse spatiotemporal data generated by event-based sensors with dense machine learning models. We propose a novel hybrid pipeline composed of asynchronous sensing and synchronous…
Traffic state data, such as speed, volume and travel time collected from ubiquitous traffic monitoring sensors require advanced network level analytics for forecasting and identifying significant traffic patterns. This paper leverages…
Users may strive to formulate an adequate textual query for their information need. Search engines assist the users by presenting query suggestions. To preserve the original search intent, suggestions should be context-aware and account for…
Given a real-world dataset, data condensation (DC) aims to synthesize a small synthetic dataset that captures the knowledge of a natural dataset while being usable for training models with comparable accuracy. Recent works propose to…