Training Watson — A Cognitive Systems Course

Authors: Michael Wollowski

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We developed a course in which students train an instance of Watson and develop an application that interacts with the trained instance. Additionally, students learn technical information about the Jeopardy! version of Watson and they discuss a future infused with cognitive assistants. In this poster, we justify this course, characterize major assessment items and provide advice on choosing a domain.
Researcher Affiliation Academia Michael Wollowski Rose-Hulman Institute of Technology wollowski@rose-hulman.edu
Pseudocode No No pseudocode or algorithm blocks were found in the paper.
Open Source Code No The paper refers to IBM-produced MOOCs and studying technical details underlying Watson, but does not provide a link or statement about releasing open-source code for the course methodology or applications developed by students.
Open Datasets No The paper mentions 'IBM recommends a training set consisting of 300 400 answers and 4 5 questions for each answer, amounting to 1200 1600 question-answer pairs.' but does not provide access information for the specific dataset(s) used in the course or by the students.
Dataset Splits No No specific dataset split information (like train/validation/test percentages or counts) was provided in the paper.
Hardware Specification No No specific hardware details (like GPU/CPU models or memory) used for running the experiments or course activities were provided in the paper.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names like Python 3.8, CPLEX 12.4) needed to replicate the activities or systems described.
Experiment Setup No The paper describes the course structure and assignments, but does not provide specific experimental setup details such as concrete hyperparameter values, training configurations, or system-level settings for the student projects or the Watson training process beyond the recommended training data size.