SBIR/STTR Research Award
An Interpretation Framework for Explanation of Machine Learning Model Decisions
Award amount
$148,350Program and phase
SBIR · Phase IAward year
2017Award details
- Awarding agency
- Department of Defense
- Branch
- Defense Advanced Research Projects Agency
- Recipient company
- MOSAIC ATM, INC.
- Proposal award date
- 2017-03-09
- Contract end date
- 2017-12-09
- UEI
- KJKXBTLUAMA5
- Solicitation number
- 2016.3
- Topic code
- SB163-007
Research abstract
In this proposed effort Mosaic ATM will study two novel techniques to generate explanations of machine learning model results for use in advanced automation-human interaction. The first technique is Explainable Principal Components Analysis, and t...
Technology keywords
Not reported
Other awards by this recipient
Verified by the same UEI. These are other public SBIR/STTR award pages, not a merged company record.
- Data Aggregation and Relay Tool (DART)
- Regulatory Ontology and Compliance Assessment Suite (ROCAS)
- Fatigue Assessment for Transportation Engineer Determination
- Trusted Research and Inference Decision Engine for Naval Tasks (TRIDENT)
- Track Nexus: Enhancing Real-Time Data Synchronization for AEGIS Combat Systems
Awards with the same topic code
Verified by an exact topic code match. This is not a text-similarity match.
- Scalable Language Association Models for Domain-specific Utterances in Novel Contexts (SLAMDUNK)
- Explainable AI to support Veterans Transition Assistance Programs (XAI-VTAP)
- Explainable Machine Learning: Training and Trust
- Deep Explainer of Neural Networks
- X-GRID: Learning Explainable Recommendations and Taxonomical Grids for Resource Allocation
Research funding history
92 SBIR/STTR records share this UEI (2005–2025). Reported award amounts total $27,087,427. Reported amounts are not federal obligations.
Phases: Phase I, Phase II
Agencies: National Aeronautics and Space Administration, Department of Defense, Department of Transportation, Department of Health and Human Services, National Science Foundation