Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Deep Neural Networks”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 235 records · Page 13

Fast inference of deep neural networks in FPGAs for particle physics

Here, recent results at the Large Hadron Collider (LHC) have pointed to enhanced physics capabilities through the improvement of the real-time event processing techniques. Machine learning methods are ubiquitous and have proven to be very powerful in LHC physics, and particle physics as a whole. However, exploration of the use of such techniques in low-latency, low-power FPGA (Field Programmable Gate Array) hardware has only just begun. FPGA-based trigger and data acquisition systems have extremely low, sub-microsecond latency requirements that are unique to particle physics. We present a case study for neural network inference in FPGAs focusing on a classifier for jet substructure which would enable, among many other physics scenarios, searches for new dark sector particles and novel measurements of the Higgs boson. While we focus on a specific example, the lessons are far-reaching. A companion compiler package for this work is developed based on High-Level Synthesis (HLS) called hls4ml to build machine learning models in FPGAs. The use of HLS increases accessibility across a broad user community and allows for a drastic decrease in firmware development time. We map out FPGA resource usage and latency versus neural network hyperparameters to identify the problems in particle physics that would benefit from performing neural network inference with FPGAs. For our example jet substructure model, we fit well within the available resources of modern FPGAs with a latency on the scale of 100 ns.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Complex Structure of Molten FLiBe (2 Li F – Be F 2 ) Examined by Experimental Neutron Scattering, X-Ray Scattering, and Deep-Neural-Network Based Molecular Dynamics

The use of molten salts as coolants, fuels, and tritium breeding blankets in the next generation of fission and fusion nuclear reactors benefits from furthering the characterization of the molecular structure of molten halide salts, paving the way to predictive capability of the chemical and thermophysical properties of molten salts. Due to its neutronic, chemical, and thermochemical properties, 2 Li F - Be F 2 is a candidate molten salt for several fusion- and fission-reactor designs. We performed neutron and x-ray total-scattering measurements to determine the atomic structure of liquid 2 Li F - Be F 2 . We also performed and neural-network molecular-dynamics simulations to predict the structure obtained by neutron- and x-ray-diffraction experiments. The use of machine learning provides improvements to the efficiency in predicting the structure at a longer length scales than is achievable with simulations at significantly lower computational expense while retaining near accuracy. We found that the NNMD simulations accurately predicted the Be F 4 2 − oligomer formations seen in the experimental first-structure-factor peak. Our combination of high-resolution measurements with large-scale molecular dynamics provided an avenue to explore and experimentally verify the intermediate-range ordering beyond the first-nearest neighbor that has posed too many experimental and computational challenges in previous works. With a deeper understanding of the salt structure and ion ordering, the evolution of salt chemistry over the lifetime of a reactor can be better predicted, which is crucial to the licensing and operation of advanced fission and fusion reactors that employ molten salts. To this end, this work will serve as a reference for future studies of salt structure and macroscopic properties with and without the addition of solutes. Published by the American Physical Society 2024

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Improving Progressive Retrieval for HPC Scientific Data using Deep Neural Network

As the disparity between compute and I/O on high-performance computing systems has continued to widen, it has become increasingly difficult to perform post-hoc data analytics on full-resolution scientific simulation data due to the high I/O cost. Error-bounded data decomposition and progressive data retrieval framework has recently been developed to address such a challenge by performing data decomposition before storage and reading only part of the decomposed data when necessary. However, the performance of the progressive retrieval framework has been suffering from the over-pessimistic error control theory, such that the achieved maximum error of recomposed data is significantly lower than the required error. Therefore, more data than required is fetched for recomposition, incurring additional I/O overhead. In order to tackle this issue, we propose a DNN-based progressive retrieval framework that can better identify the minimum amount of data to be retrieved. Our contributions are as follows: 1) We provide an in-depth investigation of the recently developed progressive retrieval framework; 2) We propose two designs of prediction models (named D-MGARD and E-MGARD) to estimate the amount of retrieved data size based on error bounds. 3) We evaluate our proposed solutions using scientific datasets generated by real-world simulations from two domains. Evaluation results demonstrate the effectiveness of our solution in accurately predicting the amount of retrieval data size, as well as the advantages of our solution over the traditional approach to reducing the I/O overhead. Based on our evaluation, our solution is shown to read significantly less data (5% - 40% with D-MGARD, 20% - 80% with E-MGARD).

Wang, Jinzhen↗

Falls Risk Classification of Older Adults Using Deep Neural Networks and Transfer Learning

Prior research in falls risk classification using inertial sensors has relied on the use of engineered features, which has concluded in a feature space containing hundreds of features that are likely redundant and possibly irrelevant. In this paper, we propose using fully convolutional neural networks (FCNNs) to classify older adults at low or high risk of falling using inertial sensor data collected from a smartphone. Due to the limited nature of older adult inertial gait data sets, we first pre-train the FCNN models using a publicly available data set for pedestrian activity recognition. Then via transfer learning, we train the network for falls risk classification. We reveal that via transfer learning, our falls risk classifier obtains an area under the receiver operating characteristic curve of 93.3%, which is 10.6% higher than the equivalent model trained without the use of transfer learning. Moreover, we show that our method outperforms other standard machine learning classifiers trained on features developed in prior research.

60 APPLIED LIFE SCIENCES↗