Engineering Papers⌕ Search

Engineering topics

Young, Steven R.

Publications and source records attributed to Young, Steven R..

Reinforcement learning applied to dilute combustion control for increased fuel efficiency

To reduce the modeling burden for control of spark-ignition engines, reinforcement learning (RL) has been applied to solve the dilute combustion limit problem. Q-learning was used to identify an optimal control policy to adjust the fuel injection quantity in each combustion cycle. A physics-based model was used to determine the relevant states of the system used for training the control policy in a data-efficient manner. The cost function was chosen such that high cycle-to-cycle variability (CCV) at the dilute limit was minimized while maintaining stoichiometric combustion as much as possible. Experimental results demonstrated a reduction of CCV after the training period with slightly lean combustion, contributing to a net increase in fuel conversion efficiency of 1.33%. To ensure stoichiometric combustion for three-way catalyst compatibility, a second feedback loop based on an exhaust oxygen sensor was incorporated into the fuel quantity controller using a slow proportional-integral (PI) controller. The closed-loop experiments showed that both feedback loops can cooperate effectively, maintaining stoichiometric combustion while reducing combustion CCV and increasing fuel conversion efficiency by 1.09%. Finally, a modified cost function was proposed to ensure stoichiometric combustion with a single controller. In addition, the learning period was shortened by half to evaluate the RL algorithm performance on limited training time. Experimental results showed that the modified cost function could achieve the desired CCV targets, however, the learning time was reduced by half and the fuel conversion efficiency increased only by 0.30%.

33 ADVANCED PROPULSION SYSTEMS↗

Combustion control using spiking neural networks

A system that controls a combustion engine stores network vectors in a memory that represent diverse and distinct spiking neural networks. The system decodes the network vectors and trains and evaluates the spiking neural networks. The system duplicates selected network vectors and crosses-over the duplicated network vectors that represent modified spiking neural networks. The system mutates the crossed-over duplicated network vectors by randomly modifying one or more portions of the crossing-over duplicated network vectors. The system meter exhaust gas into an intake manifold when an engine temperature exceeds a threshold, an engine load exceeds a threshold, an engine's rotation-per-minute rate exceeds a threshold, and a fuel flow exceeds a threshold. The system modifies fuel flow into an engine's combustion chamber on a cycle-to-cycle basis by the trained spiking neural network.

Puente, Brian P. Maldonado↗

Optimizing neural networks

A system and method design and optimize neural networks. The system and method include a data store that stores a plurality of gene vectors that represent diverse and distinct neural networks and an evaluation queue stored with the plurality of gene vectors. Secondary nodes construct, train, and evaluate the neural network and automatically render a plurality of fitness values asynchronously. A primary node executes a gene amplification on a select plurality of gene vectors, a crossing-over of the amplified gene vectors, and a mutation of the crossing-over gene vectors automatically and asynchronously, which are then transmitted to the evaluation queue. The process continuously repeats itself by processing the gene vectors inserted into the evaluation queue until a fitness level is reached, a network's accuracy level plateaus, a processing time period expires, or when some stopping condition or performance metric is met or exceeded.

97 MATHEMATICS AND COMPUTING↗

Accelerating Scientific Computing in the Post-Moore’s Era

Novel uses of graphical processing units for accelerated computation revolutionized the field of high-performance scientific computing by providing specialized workflows tailored to algorithmic requirements. As the era of Moore’s law draws to a close, many new non–von Neumann processors are emerging as potential computational accelerators, including those based on the principles of neuromorphic computing, tensor algebra, and quantum information. While development of these new processors is continuing to mature, the potential impact on accelerated computing is anticipated to be profound. We discuss how different processing models can advance computing in key scientific paradigms: machine learning and constraint satisfaction. Significantly, each of these new processor types utilizes a fundamentally different model of computation, and this raises questions about how to best use such processors in the design and implementation of applications. While many processors are being developed with a specific domain target, the ubiquity of spin-glass models and neural networks provides an avenue for multi-functional applications. Furthermore, this also hints at the infrastructure needed to integrate next-generation processing units into future high-performance computing systems.

97 MATHEMATICS AND COMPUTING↗

Deep Learning for Vertex Reconstruction of Neutrino-nucleus Interaction Events with Combined Energy and Time Data

We present a deep learning approach for vertex reconstruction of neutrino-nucleus interaction events, a problem in the domain of high energy physics. In this approach, we combine both energy and timing data that are collected in the MIN-ERvA detector to perform classification and regression tasks. We show that the resulting network achieves higher accuracy than previous results while requiring a smaller model size and less training time. In particular, the proposed model outperforms the state-of-the-art by 4.00% on classification accuracy. For the regression task, our model achieves 0.9919 on the coefficient of determination, higher than the previous work (0.96).

Song, Linghao↗

167-PFlops Deep Learning for Electron Microscopy: From Learning Physics to Atomic Manipulation

An artificial intelligence system called MENNDL, which used 25,200 Nvidia Volta GPUs on Oak Ridge National Laboratory’s Summit machine, automatically designed an optimal deep learning network in order to extract structural information from raw atomic-resolution microscopy data. In a few hours, MENNDL creates and evaluates millions of networks using a scalable, parallel, asynchronous genetic algorithm augmented with a support vector machine to automatically find a superior deep learning network topology and hyper-parameter set than a human expert can find in months. For the application of electron microscopy, the system furthers the goal of improving our understanding of the electron-beam-matter interactions and real-time image-based feedback, which enables a huge step beyond human capacity toward nanofabricating materials automatically. Finally, MENNDL has been scaled to the 4,200 available nodes of Summit achieving a measured 152.5 PFlops, with an estimated sustained performance of 167 PFlops when the entire machine is available.

97 MATHEMATICS AND COMPUTING↗

Data mining for better material synthesis: The case of pulsed laser deposition of complex oxides

The pursuit of more advanced electronics, and finding solutions to energy needs often hinges upon the discovery and optimization of new functional materials. However, the discovery rate of these materials is alarmingly low. Much of the information that could drive this rate higher is scattered across tens of thousands of papers in the extant literature published over several decades but is not in an indexed form, and cannot be used in entirety without substantial effort. Many of these limitations can be circumvented if the experimentalist has access to systematized collections of prior experimental procedures and results. Here, we investigate the property-processing relationship during growth of oxide films by pulsed laser deposition. To do so, we develop an enabling software tool to (1) mine the literature of relevant papers for synthesis parameters and functional properties of previously studied materials, (2) enhance the accuracy of this mining through crowd sourcing approaches, (3) create a searchable repository that will be a community-wide resource enabling material scientists to leverage this information, and (4) provide through the Jupyter notebook platform, simple machine-learning-based analysis to learn the complex interactions between growth parameters and functional properties. Here, the results allow visualization of growth windows, trends and outliers, which can serve as a template for analyzing the distribution of growth conditions, provide starting points for related compounds and act as a feedback for first-principles calculations. Such tools will comprise an integral part of the materials design schema in the coming decade.

36 MATERIALS SCIENCE↗

Evolving Deep Networks Using HPC

While a large number of deep learning networks have been studiedand published that produce outstanding results on natural imagedatasets, these datasets only make up a fraction of those to whichdeep learning can be applied. These datasets include text data, audiodata, and arrays of sensors that have very different characteristicsthan natural images. As these “best” networks for natural imageshave been largely discovered through experimentation and cannotbe proven optimal on some theoretical basis, there is no reasonto believe that they are the optimal network for these drasticallydifferent datasets. Hyperparameter search is thus often a very im-portant process when applying deep learning to a new problem. Inthis work we present an evolutionary approach to searching thepossible space of network hyperparameters and construction thatcan scale to 18, 000 nodes. This approach is applied to datasets ofvarying types and characteristics where we demonstrate the abilityto rapidly find best hyperparameters in order to enable practitionersto quickly iterate between idea and result.

Young, Steven↗

A Study of Complex Deep Learning Networks on High Performance, Neuromorphic, and Quantum Computers

Current Deep Learning models use highly optimized convolutional neural networks (CNN) trained on large graphical processing units (GPU)-based computers with a fairly simple layered network topology, i.e., highly connected layers, without intra-layer connections. Complex topologies have been proposed, but are intractable to train on current systems. Building the topologies of the deep learning network requires hand tuning, and implementing the network in hardware is expensive in both cost and power.In this paper, we evaluate deep learning models using three different computing architectures to address these problems: quantum computing to train complex topologies, high performance computing (HPC) to automatically determine network topology, and neuromorphic computing for a low-power hardware implementation. Due to input size limitations of current quantum computers we use the MNIST dataset for our evaluation.The results show the possibility of using the three architectures in tandem to explore complex deep learning networks that are untrainable using a von Neumann architecture. We show that a quantum computer can find high quality values of intra-layer connections and weights, while yielding a tractable time result as the complexity of the network increases; a high performance computer can find optimal layer-based topologies; and a neuromorphic computer can represent the complex topology and weights derived from the other architectures in low power memristive hardware.This represents a new capability that is not feasible with current von Neumann architecture. It potentially enables the ability to solve very complicated problems unsolvable with current computing technologies.

97 MATHEMATICS AND COMPUTING↗

Optimizing deep learning hyper-parameters through an evolutionary algorithm. In: MLHPC '15 Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments, Article No. 4

There has been a recent surge of success in utilizing Deep Learning (DL) in imaging and speech applications for its relatively automatic feature generation and, in particular for convolutional neural networks (CNNs), high accuracy classification abilities. While these models learn their parameters through data-driven methods, model selection (as architecture construction) through hyper-parameter choices remains a tedious and highly intuition driven task. To address this, Multi-node Evolutionary Neural Networks for Deep Learning (MENNDL) is proposed as a method for automating network selection on computational clusters through hyper-parameter optimization performed via genetic algorithms.

Young, Steven R.↗