Hadamard source encoding techniques applied to Apollo telemetry links - An evaluation
Hadamard transform source encoding application to Apollo unified S-band telemetry links, considering possible system performance improvement
Dawson, C. T.↗
SEARCH · Search NASA
Results for “transformer encoder”
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.
A survey of techniques for optimizing transformer inference
Recent years have seen a phenomenal rise in the performance and applications of transformer neural networks. The family of transformer networks, including Bidirectional Encoder Representations from Transformer (BERT), Generative Pretrained Transformer (GPT) and Vision Transformer (ViT), have shown their effectiveness across Natural Language Processing (NLP) and Computer Vision (CV) domains. Transformer-based networks such as ChatGPT have impacted the lives of common men. However, the quest for high predictive performance has led to an exponential increase in transformers' memory and compute footprint. Researchers have proposed techniques to optimize transformer inference at all levels of abstraction. Further, this paper presents a comprehensive survey of techniques for optimizing the inference phase of transformer networks. We survey techniques such as knowledge distillation, pruning, quantization, neural architecture search and lightweight network design at the algorithmic level. We further review hardware-level optimization techniques and the design of novel hardware accelerators for transformers. We summarize the quantitative results on the number of parameters/FLOPs and the accuracy of several models/techniques to showcase the tradeoff exercised by them. We also outline future directions in this rapidly evolving field of research. We believe that this survey will educate both novice and seasoned researchers and also spark a plethora of research efforts in this field.
97 MATHEMATICS AND COMPUTING↗
The Cortex Transform as an image preprocessor for sparse distributed memory: An initial study
An experiment is described which was designed to evaluate the use of the Cortex Transform as an image processor for Sparse Distributed Memory (SDM). In the experiment, a set of images were injected with Gaussian noise, preprocessed with the Cortex Transform, and then encoded into bit patterns. The various spatial frequency bands of the Cortex Transform were encoded separately so that they could be evaluated based on their ability to properly cluster patterns belonging to the same class. The results of this study indicate that by simply encoding the low pass band of the Cortex Transform, a very suitable input representation for the SDM can be achieved.
Olshausen, Bruno↗
Explicit Quantum Circuits for Block Encodings of Certain Sparse Matrices
Many standard linear algebra problems can be solved on a quantum computer by using recently developed quantum linear algebra algorithms that make use of block encodings and quantum eigenvalue/singular value transformations. A block encoding embeds a properly scaled matrix of interest A in a larger unitary transformation U that can be decomposed into a product of simpler unitaries and implemented efficiently on a quantum computer. Although quantum algorithms can potentially achieve exponential speedup in solving linear algebra problems compared to the best classical algorithm, such a gain in efficiency ultimately hinges on our ability to construct an efficient quantum circuit for the block encoding of A, which is difficult in general, and not trivial even for well structured sparse matrices. Here, in this paper, we give a few examples on how efficient quantum circuits can be explicitly constructed for some well structured sparse matrices and discuss a few strategies used in these constructions. We also provide implementations of these quantum circuits in MATLAB.
97 MATHEMATICS AND COMPUTING↗
Quantization Distortion in Block Transform-Compressed Data
The popular JPEG image compression standard is an example of a block transform-based compression scheme; the image is systematically subdivided into block that are individually transformed, quantized, and encoded. The compression is achieved by quantizing the transformed data, reducing the data entropy and thus facilitating efficient encoding. A generic block transform model is introduced.
block transform-compressed data quantization image↗
Optimal block cosine transform image coding for noisy channels
The two dimensional block transform coding scheme based on the discrete cosine transform was studied extensively for image coding applications. While this scheme has proven to be efficient in the absence of channel errors, its performance degrades rapidly over noisy channels. A method is presented for the joint source channel coding optimiaation of a scheme based on the 2-D block cosine transorm when the output of the encoder is to be transmitted via a memoryless design of the quantizers used for encoding the transform coefficients. This algorithm produces a set of locally optimum quantizers and the corresponding binary code assignment for the assumed transform coefficient statistics. To determine the optimum bit assignment among the transform coefficients, an algorithm was used based on the steepest descent method, which under certain convexity conditions on the performance of the channel optimized quantizers, yields the optimal bit allocation. Comprehensive simulation results for the performance of this locally optimum system over noise channels were obtained and appropriate comparisons against a reference system designed for no channel error were rendered.
Vaishampayan, Vinay A.↗
Extracting Thin Film Structures of Energy Materials Using Transformers
Not Available
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
CSGL: chemical synthesis graph learning for molecule representation
Abstract Motivation Molecule representation learning (MRL) translates molecules into a real vector space, serving as input to downstream tasks in biology, chemistry, and computer science. This article introduces a chemical synthesis graph learning (CSGL) framework, which enhances MRL by considering both the atomic structures of molecules and their roles in chemical reactions through a hierarchical graph representation. Specifically, molecules are first modeled based on their molecular graphs, which capture atomic-level structural information. They are then further refined using a chemical synthesis graph, where nodes represent reactant and product molecule sets, and edges encode chemical transformations between reactants and products (e.g. changes in molecular structures). CSGL optimizes molecular embeddings of reactant and product nodes in a fashion that ensures the embeddings conform to a chemical balance constraint. Results Experimental results show that our method CSGL achieves strong performance on a variety of tasks, including product prediction, reaction classification, and molecular property prediction. Availability and implementation https://github.com/li-2023/CSGL.
Biochemistry & Molecular Biology↗
Learning the simplicity of scattering amplitudes
The simplification and reorganization of complex expressions lies at the core of scientific progress, particularly in theoretical high-energy physics. This work explores the application of machine learning to a particular facet of this challenge: the task of simplifying scattering amplitudes expressed in terms of spinor-helicity variables. We demonstrate that an encoder-decoder transformer architecture achieves impressive simplification capabilities for expressions composed of handfuls of terms. Lengthier expressions are implemented in an additional embedding network, trained using contrastive learning, which isolates subexpressions that are more likely to simplify. The resulting framework is capable of reducing expressions with hundreds of terms—a regular occurrence in quantum field theory calculations—to vastly simpler equivalent expressions. Starting from lengthy input expressions, our networks can generate the Parke-Taylor formula for five-point gluon scattering, as well as new compact expressions for five-point amplitudes involving scalars and gravitons.
Cheung, Clifford [California Institute of Technolo↗
A review of the technology of noncontacting systems
Advanced components are the fundamental building blocks of advanced systems and spacecraft. Non-contacting elements, including magnetic bearings, brushless and ironless armature motors, rotary transformers and encoders, are discussed. Most of the information presented in this paper has been generated from a continuing program of component development. The aim of this paper is to identify some of the important design features and provide a perspective on the state of development reached to date.
Studer, P. A.↗
Applications for Subvocal Speech
A research and development effort now underway is directed toward the use of subvocal speech for communication in settings in which (1) acoustic noise could interfere excessively with ordinary vocal communication and/or (2) acoustic silence or secrecy of communication is required. By "subvocal speech" is meant sub-audible electromyographic (EMG) signals, associated with speech, that are acquired from the surface of the larynx and lingual areas of the throat. Topics addressed in this effort include recognition of the sub-vocal EMG signals that represent specific original words or phrases; transformation (including encoding and/or enciphering) of the signals into forms that are less vulnerable to distortion, degradation, and/or interception; and reconstruction of the original words or phrases at the receiving end of a communication link. Potential applications include ordinary verbal communications among hazardous- material-cleanup workers in protective suits, workers in noisy environments, divers, and firefighters, and secret communications among law-enforcement officers and military personnel in combat and other confrontational situations.
Jorgensen, Charles↗
Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers
In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or aerial wildfire operations reports to better understand the risks present. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement. These applications can benefit from the use of state-of-the-art natural language processing techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of adaptation of NLP tools to the aviation domain by fine-tuning transformer based models using aviation data sets. In 2018, a novel language model based on neural units (also called transformers) was created and became known as “Bidirectional Encoder Representations from Transformers” or BERT. This architecture combined with large amounts of English training data and innovative semi-supervised training tasks set the standard for what would later emerge as Large Language Models. The performance of these models was further improved by hyperparameter tuning and refinement of the semi-supervised training task and resulted in “Robustly Optimized BERT Pre-training Approach through hyperparameter tuning” or RoBERTa models. These pre-trained Large Language Models proved to be useful for a wide variety of natural language processing tasks such as text classification and question answering through a process called fine-tuning. The transformer architecture with pre-trained weights served as the basis with the last few layers replaced with layers fine-tuned to perform a new task e.g., a layer that provides a label for the entire input text. This process of fine-tuning can also be used to adapt the models to new domains; e.g., BioBERT started with the pre-trained BERT model and was completed by additional fine-tuning and training on biomedical documents. Transformer-based architectures can also be used to create rich representations of text called embeddings which can serve as the input to other machine learning models. This allows simpler algorithms such as logistic regression to use context-rich representations of the text while still remaining quick to train and evaluate. In the world of aviation, there is a growing demand for natural language processing and understanding but the domain presents unique challenges. Due to the technical content (and specialized language) of most aviation documents, fine-tuning pre-trained Large Language Models to specific tasks has not met the benchmark on natural language processing tasks set by simpler models trained from scratch on the data. To address this deficiency, this paper evaluates the improvements from fine-tuning a Large Language Model on a large set of aviation documents using the original semi-supervised training tasks before performing specific natural language tasks. In fine-tuning, a domain-specific dataset is used on the original training task but with the pre-trained Large Language Model instead of starting from a random initialization. This approach allows the model to be adapted to the specific domain language without discarding the information gained from training on general English data. This paper utilized two major dataset types to train and assess the RoBERTa fine-tuning performance. The first are 7,057 Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the semi-supervised fine-tuning. The second type is the 494 document classification labels to be used for evaluation. This down-stream evaluation aims to show the performance of the fine-tuned model, better understand how much data is needed for an effective fine-tuning, and how fine-tuning can be adapted for different applications in-the domain. After semi-supervised training, evaluation begins by encoding the documents for classification using the fine-tuned RoBERTa model. Then a logistic regression classifier is trained to label the document type and compared against our ground truth labels. This currently leads to a 82.8% accuracy on 10-fold cross validation showing improvement over baseline RoBERTa which achieved 81.0%. We plan to measure the improvements on additional tasks and it is expected that these improvements will lead to more robust models that can tackle the natural language processing challenges present in aviation datasets.
ATM↗
Identification of Blue Horizontal Branch Stars with Multimodal Fusion
Blue Horizontal Branch stars (BHBs) are ideal tracers to probe the global structure of the milky Way (MW), and the increased size of the BHB star sample could be helpful to accurately calculate the MW's enclosed mass and kinematics. Large survey telescopes have produced an increasing number of astronomical images and spectra. However, traditional methods of identifying BHBs are limited in dealing with the large scale of astronomical data. A fast and efficient way of identifying BHBs can provide a more significant sample for further analysis and research. Therefore, in order to fully use the various data observed and further improve the identification accuracy of BHBs, we have innovatively proposed and implemented a Bi-level attention mechanism-based Transformer multimodal fusion model, called Bi-level Attention in the Transformer with Multimodality (BATMM). The model consists of a spectrum encoder, an image encoder, and a Transformer multimodal fusion module. The Transformer enables the effective fusion of data from two modalities, namely image and spectrum, by using the proposed Bi-level attention mechanism, including cross-attention and self-attention. As a result, the information from the different modalities complements each other, thus improving the accuracy of the identification of BHBs. The experimental results show that the F1 score of the proposed BATMM is 94.78%, which is 21.77% and 2.76% higher than the image and spectral unimodality, respectively. It is therefore demonstrated that higher identification accuracy of BHBs can be achieved by means of using data from multiple modalities and employing an efficient data fusion strategy.
79 ASTRONOMY AND ASTROPHYSICS↗
Comprehensive Database of Environmental Mitigations Extracted from FERC-Licensed Hydropower Projects Using Artificial Intelligence Techniques, 1998-2023
This dataset provides a comprehensive inventory of environmental mitigation measures required by Federal Energy Regulatory Commission (FERC) licensed hydropower facilities from 461 licenses that were issued from 1998 to 2023. These licenses constitute 446 of the 1015 FERC projects that were active at the end of 2023. 17,612 mentions of environmental mitigations were identified and categorized in 128 unique categories. Mitigations were identified using a Natural Language Processing (NLP) approach, specifically with a Bidirectional Encoder Representations from Transformer (BERT) model. Model-derived results were then reviewed and updated by a subject matter expert as needed. This dataset introduces important enhancements to previous efforts to inventory environmental mitigations, such as including associated license text for each mitigation, tracking the number of instances a mitigation was identified within a license, and providing improved location information. These enhancements significantly expand the dataset's utility, offering greater analytical capabilities and ensuring reproducibility. The dataset is downloadable as a zip file containing the metadata and dataset files.
Ruggles, Thomas [Oak Ridge National Laboratory (OR↗
Regulated dc-to-dc converter for voltage step-up or step-down with input-output isolation.
A dc-to-dc regulated-converter circuit employing duty-cycle control with variable on and variable off time has been presented. A unique feature of this converter is the method by which the bistable-comparator output controls the duty cycle of the power switching transistor through the action of the encoder. The utilization of minor-loop flux excursions of a saturable-core transformer in the encoder makes it feasible to extend the converter switching frequency considerably higher than would normally be possible. With this converter circuit, high and very-high frequency converter operations were explored.
Feng, S. Y. M.↗
Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers
In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or create more accurate transcripts of air traffic management conversations. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement (LOA) which is used as the evaluation case in this paper. These applications can benefit from the use of state-of-the-art Natural Language Processing (NLP) techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of transferring pre-trained large language models to the aviation domain by adapting transformer based models using aviation datasets. This paper utilized two datasets to adapt a ‘Robustly Optimized Bidirectional Encoder Representations from Transformers Approach’ (RoBERTa) model and two down-stream classification tasks to assess its performance. These datasets are all built upon Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. The first two datasets are used for the adaptation of RoBERTa to the aviation domain and were of different sizes to assess the number of documents needed to adapt to the aviation domain. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the unsupervised adaptation. The second dataset is a separate set of LOA documents with two sets of classification labels to be used for evaluation; one at the document level and one at the line level. These down-stream evaluations allowed the measurement of improvement by adapting RoBERTa. The accuracy increased by 4-6% on both tasks and the F1 score on the class of interest increased by 4-8% from the adaptation.
Air Traffic Management↗
Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers
In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or create more accurate transcripts of air traffic management conversations. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement (LOA) which is used as the evaluation case in this paper. These applications can benefit from the use of state-of-the-art Natural Language Processing (NLP) techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of transferring pre-trained large language models to the aviation domain by adapting transformer based models using aviation datasets. This paper utilized two datasets to adapt a ‘Robustly Optimized Bidirectional Encoder Representations from Transformers Approach’ (RoBERTa) model and two down-stream classification tasks to assess its performance. These datasets are all built upon Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. The first two datasets are used for the adaptation of RoBERTa to the aviation domain and were of different sizes to assess the number of documents needed to adapt to the aviation domain. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the unsupervised adaptation. The second dataset is a separate set of LOA documents with two sets of classification labels to be used for evaluation; one at the document level and one at the line level. These down-stream evaluations allowed the measurement of improvement by adapting RoBERTa. The accuracy increased by 4-6% on both tasks and the F1 score on the class of interest increased by 4-8% from the adaptation.
Air Traffic Management↗
The fast decoding of Reed-Solomon codes using number theoretic transforms
It is shown that Reed-Solomon (RS) codes can be encoded and decoded by using a fast Fourier transform (FFT) algorithm over finite fields. The arithmetic utilized to perform these transforms requires only integer additions, circular shifts and a minimum number of integer multiplications. The computing time of this transform encoder-decoder for RS codes is less than the time of the standard method for RS codes. More generally, the field GF(q) is also considered, where q is a prime of the form K x 2 to the nth power + 1 and K and n are integers. GF(q) can be used to decode very long RS codes by an efficient FFT algorithm with an improvement in the number of symbols. It is shown that a radix-8 FFT algorithm over GF(q squared) can be utilized to encode and decode very long RS codes with a large number of symbols. For eight symbols in GF(q squared), this transform over GF(q squared) can be made simpler than any other known number theoretic transform with a similar capability. Of special interest is the decoding of a 16-tuple RS code with four errors.
Reed, I. S.↗