GraphSAGE
GraphSAGE is a framework for inductive representation learning on large graphs. It generates node embeddings by sampling and aggregating features from a node’s local neighborhood, enabling scalable and generalizable graph learning.
Technology & Innovation
SHAP (Shapley additive explanations)
SHAP (Shapley Additive Explanations) is a method for explaining the output of machine learning models, providing insights into feature contributions.
Supervised learning
Supervised learning is a type of machine learning where models are trained on labeled data to make predictions or classify new data. It involves using input-output pairs to guide the learning process.
QMIX (multi-agent reinforcement learning)
QMIX is a multi-agent reinforcement learning algorithm designed to enable efficient coordination among multiple agents in complex environments.
Radial basis function network
Radial Basis Function Networks (RBFNs) are a type of artificial neural network that uses radial basis functions as activation functions. They are primarily used for pattern recognition and function approximation.
DARPA Artificial Intelligence programs
DARPA Artificial Intelligence programs are research initiatives funded by the Defense Advanced Research Projects Agency aimed at advancing AI technologies for defense and national security applications. These programs focus on developing innovative AI methods including machine learning, autonomous systems, and human-AI collaboration.
Batch ensemble
Batch ensemble is a machine learning technique designed to improve the efficiency and scalability of ensemble models by sharing parameters across multiple ensemble members, enabling more practical uncertainty estimation and robustness in neural networks.
SwAV (swapping assignments between views)
SwAV is a self-supervised learning method in computer vision that enables effective learning by swapping assignments between different views of data.
M3E (multilingual massive model embedding)
M3E (multilingual massive model embedding) is a technology in natural language processing that creates embeddings capable of representing multiple languages in a single vector space. It is designed to improve cross-lingual understanding and processing in large-scale multilingual applications.
Learning from demonstrations
Learning from demonstrations (LfD) is a technique in machine learning and robotics where systems acquire new skills by observing and imitating human or expert behavior. This approach enables the development of algorithms that can replicate complex tasks without explicit programming, facilitating more intuitive human-robot interaction and adaptive automation.