I.9 Interactive Learning in Triage Tactics

Sharkzor: Interactive Deep Learning for Image Triage, Sort and Summary

Sharkzor is a web application for machinelearning assisted image sort and summary. Deep learning algorithms are leveraged to infer, augment, and automate the user’s mental model. Initially, images uploaded by the user are spread out on a canvas. The user then interacts with the images to impute their mental model into the applications algorithmic underpinnings. Methods of interaction within Sha...

Learning to Prove with Tactics

We implement a automated tactical prover TacticToe on top of the HOL4 interactive theorem prover. TacticToe learns from human proofs which mathematical technique is suitable in each proof situation. This knowledge is then used in a Monte Carlo tree search algorithm to explore promising tactic-level proof paths. On a single CPU, with a time limit of 60 seconds, TacticToe proves 66.4% of the 7164...

TacticToe: Learning to Reason with HOL4 Tactics

Applying Affective Tactics for a Better Learning

This paper describes the Mediating Agent, an animated pedagogical agent inserted in a computational system for distance learning, which has the goal of motivating the student to learn as well as promoting a positive mood in the student, which is more appropriate to learning. In order to accomplish its function, the agent should recognize the student’s emotions to respond appropriately. Thus, it...

TACTICS, an interactive platform for customized high-content bioimaging analysis

We describe a modular MATLAB® Toolbox named TACTICS for time-lapse image analysis that meets several requirements not generally offered by currently available software packages: (i) the ability to assess quality of extracted imaging information by directly linking data end points to the original position, (ii) massively parallel analysis of each parameter, for flow cytometry-like assessment of ...