Learning Algorithms

Learning Algorithms

Machine Learning determines rules or behaviors from data that can be generalized and applied to new data. Applications of machine learning are growing rapidly—benefitting from increasingly affordable computation and a proverbial data deluge—but the raw data that a machine learner needs is often ill-suited for direct input. GDA’s approaches extract informative features and reduce the computational complexity and dimensionality of non-traditional or high-dimensional data types, expanding the utility of machine learning approaches. Within general machine-learning, GDA has specialties in reinforcement learning, distributed learning, and active learning.

Reinforcement learning

Many applications require answers to how a system should act or react to information to achieve a goal. Reinforcement learning (RL) is a collection of techniques to develop optimal actions or controls in the face of limited information. Such collections of optimal actions are called a policy. Using deep neural networks to approximate policies has opened new applications up to reinforcement learning—more descriptively deep reinforcement learning. RL solutions are complex, computationally intensive, and often ill-defined.

GDA applies disciplined software development and research capabilities to extend existing reinforcement learning algorithms and practices to address a variety of multi-agent problems (e.g. controlling a group of UAV or sensors). Our team of experts create efficient computing solutions and work closely with subject matter experts to define and refine optimal solutions to RL problems in decision support models, power distribution, and cybersecurity.

Distributed machine learning

In many modern IoT applications, processing of input and subsequent inference happens in different locations, termed distributed machine learning. Typically, the former is “on the edge” and the latter is “in the cloud.” Specific mission conditions often dictate that one must be very mindful of how much information is transmitted between edge and cloud. These communication and computation constraints can limit the application of machine learning approaches.

GDA’s cutting-edge work on informative compressed representations and featurizations, based in shape analytics, allow information-rich summaries to be computed on the edge and powerful machine learning to take place in the cloud. This facilitates essential optimization of storage, processing, transmission, and learning.

Active Machine Learning

Many machine learning applications benefit tremendously from repeated subject-matter expert input and refinement. Semi-automated or active machine learning methods enable experts to provide direct, rapid feedback during model development. GDA has active learning frameworks that keep the critical human in-the-loop, resulting in higher quality, usable model output.

Our active learning framework is currently being used by plant scientists studying the rhizosphere. Efficient and accurate image featurization and classification of complex images of underground roots enables lower-cost, higher-throughput agricultural research.