Search Results for author: Vladimir Loncar

Found 19 papers, 8 papers with code

Sets are all you need: Ultrafast jet classification on FPGAs for HL-LHC

no code implementations2 Feb 2024 Patrick Odagiu, Zhiqiang Que, Javier Duarte, Johannes Haller, Gregor Kasieczka, Artur Lobanov, Vladimir Loncar, Wayne Luk, Jennifer Ngadiuba, Maurizio Pierini, Philipp Rincke, Arpita Seksaria, Sioni Summers, Andre Sznajder, Alexander Tapper, Thea K. Aarrestad

We study various machine learning based algorithms for performing accurate jet flavor classification on field-programmable gate arrays and demonstrate how latency and resource consumption scale with the input size and choice of algorithm.

Quantization

Ultra Fast Transformers on FPGAs for Particle Physics Experiments

no code implementations1 Feb 2024 Zhixing Jiang, Dennis Yin, Elham E Khoda, Vladimir Loncar, Ekaterina Govorkova, Eric Moreno, Philip Harris, Scott Hauck, Shih-Chieh Hsu

This work introduces a highly efficient implementation of the transformer architecture on a Field-Programmable Gate Array (FPGA) by using the \texttt{hls4ml} tool.

SymbolNet: Neural Symbolic Regression with Adaptive Dynamic Pruning

no code implementations18 Jan 2024 Ho Fung Tsoi, Vladimir Loncar, Sridhara Dasu, Philip Harris

Contrary to the use of genetic programming, the neural network approach to symbolic regression can scale well with high input dimension and leverage gradient methods for faster equation searching.

Jet Tagging regression +1

FPGA Resource-aware Structured Pruning for Real-Time Neural Networks

no code implementations9 Aug 2023 Benjamin Ramhorst, Vladimir Loncar, George A. Constantinides

Neural networks achieve state-of-the-art performance in image classification, speech recognition, scientific analysis and many more application areas.

Classification Image Classification +4

Symbolic Regression on FPGAs for Fast Machine Learning Inference

no code implementations6 May 2023 Ho Fung Tsoi, Adrian Alan Pol, Vladimir Loncar, Ekaterina Govorkova, Miles Cranmer, Sridhara Dasu, Peter Elmer, Philip Harris, Isobel Ojalvo, Maurizio Pierini

The high-energy physics community is investigating the potential of deploying machine-learning-based solutions on Field-Programmable Gate Arrays (FPGAs) to enhance physics sensitivity while still meeting data processing time constraints.

Neural Architecture Search regression +1

Tailor: Altering Skip Connections for Resource-Efficient Inference

no code implementations18 Jan 2023 Olivia Weng, Gabriel Marcano, Vladimir Loncar, Alireza Khodamoradi, Nojan Sheybani, Andres Meza, Farinaz Koushanfar, Kristof Denolf, Javier Mauricio Duarte, Ryan Kastner

We argue that while a network's skip connections are needed for the network to learn, they can later be removed or shortened to provide a more hardware efficient implementation with minimal to no accuracy loss.

QONNX: Representing Arbitrary-Precision Quantized Neural Networks

1 code implementation15 Jun 2022 Alessandro Pappalardo, Yaman Umuroglu, Michaela Blott, Jovan Mitrevski, Ben Hawks, Nhan Tran, Vladimir Loncar, Sioni Summers, Hendrik Borras, Jules Muhizi, Matthew Trahms, Shih-Chieh Hsu, Scott Hauck, Javier Duarte

We present extensions to the Open Neural Network Exchange (ONNX) intermediate representation format to represent arbitrary-precision quantized neural networks.

Quantization

Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml

no code implementations16 May 2022 Nicolò Ghielmetti, Vladimir Loncar, Maurizio Pierini, Marcel Roed, Sioni Summers, Thea Aarrestad, Christoffer Petersson, Hampus Linander, Jennifer Ngadiuba, Kelvin Lin, Philip Harris

In this paper, we investigate how field programmable gate arrays can serve as hardware accelerators for real-time semantic segmentation tasks relevant for autonomous driving.

Autonomous Driving Quantization +1

A reconfigurable neural network ASIC for detector front-end data compression at the HL-LHC

no code implementations4 May 2021 Giuseppe Di Guglielmo, Farah Fahim, Christian Herwig, Manuel Blanco Valentin, Javier Duarte, Cristian Gingu, Philip Harris, James Hirschauer, Martin Kwok, Vladimir Loncar, Yingyi Luo, Llovizna Miranda, Jennifer Ngadiuba, Daniel Noonan, Seda Ogrenci-Memik, Maurizio Pierini, Sioni Summers, Nhan Tran

We demonstrate that a neural network autoencoder model can be implemented in a radiation tolerant ASIC to perform lossy data compression alleviating the data transmission problem while preserving critical information of the detector energy profile.

Data Compression Quantization

Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors

3 code implementations15 Jun 2020 Claudionor N. Coelho Jr., Aki Kuusela, Shan Li, Hao Zhuang, Thea Aarrestad, Vladimir Loncar, Jennifer Ngadiuba, Maurizio Pierini, Adrian Alan Pol, Sioni Summers

Although the quest for more accurate solutions is pushing deep learning research towards larger and more complex algorithms, edge devices demand efficient inference and therefore reduction in model size, latency and energy consumption.

Quantization

Fast inference of Boosted Decision Trees in FPGAs for particle physics

3 code implementations5 Feb 2020 Sioni Summers, Giuseppe Di Guglielmo, Javier Duarte, Philip Harris, Duc Hoang, Sergo Jindariani, Edward Kreinar, Vladimir Loncar, Jennifer Ngadiuba, Maurizio Pierini, Dylan Rankin, Nhan Tran, Zhenbin Wu

We describe the implementation of Boosted Decision Trees in the hls4ml library, which allows the translation of a trained model into FPGA firmware through an automated conversion process.

Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.