AI Chat AI Image Generator AI Video Text to Speech

Position Paper: Towards Transparent Machine Learning

11/12/2019

∙

by Dustin Juliano, et al.

∙

∙

Transparent machine learning is introduced as an alternative form of machine learning, where both the model and the learning system are represented in source code form. The goal of this project is to enable direct human understanding of machine learning models, giving us the ability to learn, verify, and refine them as programs. If solved, this technology could represent a best-case scenario for the safety and security of AI systems going forward.

page 1

page 2

page 3

page 4

research

∙ 10/06/2019

Using Deep Learning and Machine Learning to Detect Epileptic Seizure with Electroencephalography (EEG) Data

The prediction of epileptic seizure has always been extremely challengin...

0 Haotian Liu, et al. ∙

research

∙ 12/16/2018

The Adverse Effects of Code Duplication in Machine Learning Models of Code

The field of big code relies on mining large corpora of code to perform ...

0 Miltiadis Allamanis, et al. ∙

research

∙ 10/05/2018

Model Cards for Model Reporting

Trained machine learning models are increasingly used to perform high-im...

6 Margaret Mitchell, et al. ∙

research

∙ 08/04/2020

Machine Learning in Ethnobotany – a first experiment

We describe new opportunities afforded by bring A.I to the field of ethn...

0 Marc Böhlen, et al. ∙

research

∙ 04/21/2023

Tokenization Tractability for Human and Machine Learning Model: An Annotation Study

Is tractable tokenization for humans also tractable for machine learning...

0 Tatsuya Hiraoka, et al. ∙

research

∙ 11/09/2020

Risk Assessment for Machine Learning Models

In this paper we propose a framework for assessing the risk associated w...

21 Paul Schwerdtner, et al. ∙

research

∙ 05/25/2022

Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophy

In an effort to guarantee that machine learning model outputs conform wi...

20 Kathleen C. Fraser, et al. ∙