PWS.doc
DOC document 82 KB Posted
- Solicitation number
- W911QX-24-Q-0217
About this file
This document is a Performance Work Statement (PWS) for MATLAB Machine Learning Advisory and Consulting Services for the Army Research Laboratory (ARL).
The PWS outlines the requirement for the contractor to provide deep learning advisory, customized training, and MATLAB script development to support ARL's use of MATLAB for artificial intelligence (AI) applications and complex scientific research. Key objectives include analyzing provided materials to define an AI problem, reviewing data collection issues and creating sample codes, implementing data pre-processing and preparation, and developing sample programs for deep neural networks, machine learning models, and image/data processing algorithms for classification and regression forecasting.
The required deliverables include a training database, machine learning regression and classification models, validation of the ML models, and prediction of new materials with enhanced nonlinear optical properties. The period of performance is two years, with a final technical report due 30 days prior to the end of the period.
View the file
Other files
| File | Type | Posted |
|---|---|---|
| DD1423_MathWorks - Redacted.pdf | ||
| Provisions and Clauses Full-Text Attachment.docx | DOCX document | |
| Combination Synopsis-Solicitation for Commercial Purchases (Under SAT)_W911QX24Q0217.docx | DOCX document |
On GovTribe
Work with this file
- Download the original file
- Contacts named in this file
- Similar government files
- Ask GovTribe AI about this file
Text version
Performance Work Statement (PWS)
MATLAB Machine Learning Advisory and Consulting Services 24 June 2024 C.1 Background
The Army Research Laboratory (ARL) is a user of MATLAB software for conducting complex scientific research. The ARL is researching a variety of artificial intelligence (AI) applications and currently uses the MATLAB software to conduct complex scientific research. The required advisory/consulting services will further support ARL in how to best employ MATLAB and its toolbox capabilities, and consist of the sole source, MathWorks, to review ARL’s existing MATLAB codes and aid in the development of deep learning/machine learning model architecture, data processing, and model test/evaluation.
C.2 Objective
MATLAB Machine Learning Advisory and consulting services are being sought for developing Machine Learning scripts for two-dimensional (2D) nonlinear optical (NLO) material database-based material properties classification and regression. Therefore, under this effort, the Contractor shall provide deep learning advisory, customized training, and MATLAB script development to support ARL mission programs.
C.3 Requirement C.3.1 The Contractor shall analyze provided papers and outline a possible workflow solution for defining an artificial intelligence (AI) problem.
C.3.2 The Contractor shall review and support data collection issues, create sample codes for importing spreadsheet data, and create sample codes for processing information that can be translated into usable data in a machine learning framework.
C.3.3 The Contractor shall implement data pre-processing and preparation using MATLAB platform by creating sample codes and preparing a data table to be used in machine learning.
C.3.4 The Contractor shall create sample programs on how to develop Deep Neural Networks (DNN), machine learning models, and image/data processing algorithms for classification and regression forecasting.
C.4 Contract Deliverables
C.4.1 Training data base of the 2D material (a) chemical, geometrical, and electronic structures, (b) optical parameters shall be delivered to the technical point of contact (TPOC) no later than (NLT) 12 months after award.
C.4.2 Machine Learning regression models specifically tailored to forecast the formation energy of nonlinear crystals shall be delivered to the TPOC NLT 12 months after award.
C.4.3 Machine Learning classification models specifically tailored to discovering infrared nonlinear optical crystals with superior properties shall be delivered to the TPOC NLT 12 months after award.
C.4.4 Validation of the ML models against learning data base shall be delivered to the TPOC NLT 18 months after award.
C.4.5 Prediction of new materials system with enhanced NLO properties shall be delivered to the TPOC NLT 18 months after award. Total anticipated period of performance is two (2) years.
C.4.6 A final technical report is required to be submitted to the Tech POC via email NLT 30 days prior to the period of performance end date. The final report shall be in the Contractor’s preferred format and describe the outcomes of the performed services.
C.5 Distribution
C.5.1 Determination of Contract submission documents and information generated during contract performance are:
DISTRIBUTION STATEMENT A. Approved for public release; distribution is unlimited.
Contracting Officer:
File details come from the government source that posted it. Updated .