A System for Accessible Artificial Intelligence

  title={A System for Accessible Artificial Intelligence},
  author={Randal S. Olson and Moshe Sipper and W. L. Cava and Sharon Tartarone and Steve Vitale and Weixuan Fu and John H. Holmes and Jason H. Moore},
While artificial intelligence (AI) has become widespread, many commercial AI systems are not yet accessible to individual researchers nor the general public due to the deep knowledge of the systems required to use them. We believe that AI has matured to the point where it should be an accessible technology for everyone. We present an ongoing project whose ultimate goal is to deliver an open source, user-friendly AI system that is specialized for machine learning analysis of complex data in the… 

Preparing next-generation scientists for biomedical big data: artificial intelligence approaches.

This work reviews several areas of knowledge that are necessary for next-generation scientists to fully realize the potential of biomedical big data, including statistics and data science as foundational topics followed by a core curriculum of artificial intelligence, machine learning and natural language processing.

Evaluating recommender systems for AI-driven biomedical informatics

The proposed AI is competitive with state-of-the-art automated ML methods in terms of choosing optimal algorithm configurations for datasets and produces a competent ML model that performs on par with state of theart deep learning results for this task, with much less computational effort.

A Review on Automated Machine Learning (AutoML) Systems

The strongholds and drawbacks of the various approaches and their reviews in terms of algorithms supported, features and the implementations are explored and a design that will meet the gaps and the missing links identified is created.

The promise of automated machine learning for the genetic analysis of complex traits

The promise of AutoML is to enable anyone, regardless of training or expertise, to apply machine learning as part of their genetic analysis strategy and it is hoped that this review will motivate studies to develop and evaluate novel AutoML methods and software in the genetics and genomics space.

A Visual Framework for Transparent and Accessible Machine Learning

This paper presents a visual framework to make ML more accessible and interpretable for users without data science expertise and studies how Human Computer Interaction, Visual Languages, Auto Machine Learning and Explainable Artificial Intelligence can help in making ML more user-friendly.

Ten quick tips for machine learning in computational biology

  • D. Chicco
  • Biology, Computer Science
    BioData Mining
  • 2017
Ten quick tips to take advantage of machine learning in any computational biology context, by avoiding some common errors that the authors observed hundreds of times in multiple bioinformatics projects are presented.

Grammatical Evolution Strategies for Bioinformatics and Systems Genomics

Grammatical evolution (GE) is a promising example of evolutionary computing because it generates solutions to a problem using a generative grammar and can utilize expert knowledge and consider multiple fitness criteria.

Benchmarking AutoML algorithms on a collection of binary problems

It is found that AutoML can identify pipelines that perform well on all included datasets and some were more consistent than others at finding high-performing solutions for some datasets.

An Extensive Checklist for Building AutoML Systems

An analysis of the components and technologies in the domains of autoML, hyperparameter tuning and meta learning and, presents a checklist of steps to follow while building an AutoML system will assist in developing a novel architecture.

Investigating the parameter space of evolutionary algorithms

It is shown that parameter space tends to be rife with viable parameters, at least for the problems studied herein, and the implications for researcher employing EC are discussed.



Development and Evaluation of an Open-Ended Computational Evolution System for the Genetic Analysis of Susceptibility to Common Human Diseases

This work develops and evaluates a prototype CE system for the analysis of human genetics data and provides initial results from a simulation study that suggests more complex operators result in better solutions.

Genetic Programming Representations for Multi-dimensional Feature Learning in Biomedical Classification

A new classification method that uses genetic programming (GP) to evolve feature transformations for a deterministic, distanced-based classifier that outperforms other GP methods for classification and exhibits the ability to detect epistatic interactions better than the other methods.

Toward the automated analysis of complex diseases in genome-wide association studies using genetic programming

An open source pipeline optimization tool (TPOT-MDR) that uses genetic programming to automatically design machine learning pipelines for bioinformatics studies and significantly outperforms modern machine learning methods such as logistic regression and eXtreme Gradient Boosting.

Multiple Objective Vector-Based Genetic Programming Using Human-Derived Primitives

The GTMOEP framework was applied to the problem of predicting how long an emergency responder can remain in a hazmat suit before the effects of heat stress cause the user to become unsafe, resulting in a safer algorithm for emergency responders to determine operating times in harsh environments.

TPOT: A Tree-based Pipeline Optimization Tool for Automating Machine Learning

This chapter presents TPOT v0.3, an open source genetic programming-based AutoML system that optimizes a series of feature preprocessors and machine learning models with the goal of maximizing classification accuracy on a supervised classification task.

Human-Computer Interaction in a Computational Evolution System for the Genetic Analysis of Cancer

The incorporation of human-computer interaction into CES provides a first step towards an interactive discovery system where the experts can be embedded in the computational discovery process, and the use of 3D visualization methods to identify interesting patterns in CES results is introduced.

Exploring Interestingness in a Computational Evolution System for the Genome-Wide Genetic Analysis of Alzheimer's Disease

This study demonstrates the applicability of CES to genome-wide genetic analysis using expert knowledge derived from measures of interestingness to discover more interesting models with the added benefit of improving classification accuracy.

PMLB: a large benchmark suite for machine learning evaluation and comparison

It is found that existing benchmarks lack the diversity to properly benchmark machine learning algorithms, and there are several gaps in benchmarking problems that still need to be considered.

Genome-Wide Genetic Analysis Using Genetic Programming: The Critical Need for Expert Knowledge

It is demonstrated that GP may be a useful computational discovery tool in this domain by including pre-processed estimates of attribute quality using Tuned ReliefF (TuRF) in a multi-objective fitness function that also includes accuracy significantly improves the performance of GP over that of random search.

A General Feature Engineering Wrapper for Machine Learning Using \epsilon -Lexicase Survival

The proposed feature engineering wrapper (FEW) uses genetic programming to represent and evolve individual features tailored to the machine learning method with which it is paired, and is able to improve model test predictions across problems for several ML methods.