Related papers: The ONSEN Data Reduction System for the Belle II P…

The Time-Of-Propagation detector is a Cherenkov particle identification detector based on quartz radiator bars for the Belle II experiment at the SuperKEKB electron-positron collider. The purpose of the detector is to identify the type of…

A robust real-world deployment of autonomous edge devices requires on-chip adaptation to user-, environment- and task-induced variability. Due to on-chip memory constraints, prior learning devices were limited to static stimuli with no…

Research has shown that convolutional neural networks contain significant redundancy, and high classification accuracy can be obtained even when weights and activations are reduced from floating point to binary values. In this paper, we…

Transformer-based models excel in speech recognition. Existing efforts to optimize Transformer inference, typically for long-context applications, center on simplifying attention score calculations. However, streaming speech recognition…

CNNs have been shown to maintain reasonable classification accuracy when quantized to lower precisions. Quantizing to sub 8-bit activations and weights can result in accuracy falling below an acceptable threshold. Techniques exist for…

A new FPGA-based low-level trigger processor has been installed at the NA62 experiment. It is intended to extend the features of its predecessor due to a faster interconnection technology and additional logic resources available on the new…

Belle II is a new-generation B-factory experiment, dedicated to exploring new physics beyond the standard model of elementary particles in the flavor sector. Belle~II started data-taking in April 2018, using a synchronous data acquisition…

Event-cameras have emerged as a revolutionary technology with a high temporal resolution that far surpasses standard active pixel cameras. This technology draws biological inspiration from photoreceptors and the initial retinal synapse.…

The last few years have brought advances in computer vision at an amazing pace, grounded on new findings in deep neural network construction and training as well as the availability of large labeled datasets. Applying these networks to…

To accelerate inference of Convolutional Neural Networks (CNNs), various techniques have been proposed to reduce computation redundancy. Converting convolutional layers into frequency domain significantly reduces the computation complexity…

In the next decade, intensity frontier experiments will require tracking systems that are robust against high event and background rates while maintaining excellent tracking performance. We develop a first conceptual design of a tracking…

We present Occamy, a 432-core RISC-V dual-chiplet 2.5D system for efficient sparse linear algebra and stencil computations on FP64 and narrow (32-, 16-, 8-bit) SIMD FP data. Occamy features 48 clusters of RISC-V cores with custom…

With the rapidly-developing high-speed wireless communications, the 60 GHz millimeter-wave frequency range and radio-over-fiber systems have been investigated as a promising solution to deliver mm-wave signals. Neural networks have been…

ALICE has upgraded many of its detectors for LHC Run 3 to operate in continuous readout mode recording Pb--Pb collisions at 50 kHz interaction rate without trigger. This results in the need to process data in real time at rates 100 times…

We describe a neural network for predicting the background hit rate in the Belle II detector produced by the SuperKEKB electron-positron collider. The neural network, BGNet, learns to predict the individual contributions of different…

Introducing HyperSense, our co-designed hardware and software system efficiently controls Analog-to-Digital Converter (ADC) modules' data generation rate based on object presence predictions in sensor data. Addressing challenges posed by…

In this paper, we propose a low-power hardware for efficient deployment of binarized neural networks (BNNs) that have been trained for physiological datasets. BNNs constrain weights and feature-map to 1 bit, can pack in as many 1-bit…

Modern diffusion-based image generative models have made significant progress and become promising to enrich training data for the object detection task. However, the generation quality and the controllability for complex scenes containing…

Though CNNs are highly parallel workloads, in the absence of efficient on-chip memory reuse techniques, an accelerator for them quickly becomes memory bound. In this paper, we propose a CNN accelerator design for inference that is able to…

Deep convolutional neural networks have achieved remarkable progress in recent years. However, the large volume of intermediate results generated during inference poses a significant challenge to the accelerator design for…