415 citations · 725 across the 47 of their papers we have counts for
51 papers
GPU-Accelerated Rule Evaluation and Evolution
Hormoz Shahrzad, Risto Miikkulainen
This paper introduces an innovative approach to boost the efficiency and scalability of Evolutionary Rule-based machine Learning (ERL), a key technique in explainable AI. While tra…
Asynchronous Evolution of Deep Neural Network Architectures
Jason Liang, Hormoz Shahrzad, Risto Miikkulainen
Many evolutionary algorithms (EAs) take advantage of parallel evaluation of candidates. However, if evaluation times vary significantly, many worker nodes (i.e.,\ compute clients)…
Evolving Strategies for Competitive Multi-Agent Search
Erkin Bahceci, Riitta Katila, Risto Miikkulainen
While evolutionary computation is well suited for automatic discovery in engineering, it can also be used to gain insight into how humans and organizations could perform more effec…
Accelerating Evolution Through Gene Masking and Distributed Search
Hormoz Shahrzad, Risto Miikkulainen
In building practical applications of evolutionary computation (EC), two optimizations are essential. First, the parameters of the search method need to be tuned to the domain in o…
Efficient Activation Function Optimization through Surrogate Modeling
Garrett Bingham, Risto Miikkulainen
Carefully designed activation functions can improve the performance of neural networks in many machine learning tasks. However, it is difficult for humans to construct optimal acti…
Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search
Xin Qiu, Risto Miikkulainen
Population-based search has recently emerged as a possible alternative to Reinforcement Learning (RL) for black-box neural architecture search (NAS). It performs well in practice e…
Effective Mutation Rate Adaptation through Group Elite Selection
Akarsh Kumar, Bo Liu, Risto Miikkulainen +1
Evolutionary algorithms are sensitive to the mutation rate (MR); no single value of this parameter works well across domains. Self-adaptive MR approaches have been proposed but the…
EVOTER: Evolution of Transparent Explainable Rule-sets
Hormoz Shahrzad, Babak Hodjat, Risto Miikkulainen
Most AI systems are black boxes generating reasonable outputs for given inputs. Some domains, however, have explainability and trustworthiness requirements that cannot be directly…
DIAS: A Domain-Independent Alife-Based Problem-Solving System
Babak Hodjat, Hormoz Shahrzad, Risto Miikkulainen
A domain-independent problem-solving system based on principles of Artificial Life is introduced. In this system, DIAS, the input and output dimensions of the domain are laid out i…
Simple Genetic Operators are Universal Approximators of Probability Distributions (and other Advantages of Expressive Encodings)
Elliot Meyerson, Xin Qiu, Risto Miikkulainen
This paper characterizes the inherent power of evolutionary algorithms. This power depends on the computational properties of the genetic encoding. With some encodings, two parents…
NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
Wenxi Wang, Yang Hu, Mohit Tiwari +3
Propositional satisfiability (SAT) is an NP-complete problem that impacts many research fields, such as planning, verification, and security. Mainstream modern SAT solvers are base…
AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks
Garrett Bingham, Risto Miikkulainen
Neural networks require careful weight initialization to prevent signals from exploding or vanishing. Existing initialization schemes solve this problem in specific cases by assumi…
Evolving GAN Formulations for Higher Quality Image Synthesis
Santiago Gonzalez, Mohak Kant, Risto Miikkulainen
Generative Adversarial Networks (GANs) have extended deep learning to complex generation and translation tasks across different data modalities. However, GANs are notoriously diffi…
The Traveling Observer Model: Multi-task Learning Through Spatial Variable Embeddings
Elliot Meyerson, Risto Miikkulainen
This paper frames a general prediction system as an observer traveling around a continuous space, measuring values at some locations, and predicting them at others. The observer is…
Detecting Misclassification Errors in Neural Networks with a Gaussian Process Model
Xin Qiu, Risto Miikkulainen
As neural network classifiers are deployed in real-world applications, it is crucial that their failures can be detected reliably. One practical solution is to assign confidence sc…
Creative AI Through Evolutionary Computation: Principles and Examples
Risto Miikkulainen
The main power of artificial intelligence is not in modeling what we already know, but in creating solutions that are new. Such solutions exist in extremely large, high-dimensional…
Characterizing the Effect of Sentence Context on Word Meanings: Mapping Brain to Behavior
N. Aguirre-Celis, R. Miikkulainen
Semantic feature models have become a popular tool for prediction and interpretation of fMRI data. In particular, prior work has shown that differences in the fMRI patterns in sent…
Generalization of Agent Behavior through Explicit Representation of Context
Cem C Tutum, Suhaib Abdulquddos, Risto Miikkulainen
In order to deploy autonomous agents in digital interactive environments, they must be able to act robustly in unseen situations. The standard machine learning approach is to inclu…
Discovering Parametric Activation Functions
Garrett Bingham, Risto Miikkulainen
Recent studies have shown that the choice of activation function can significantly affect the performance of deep learning networks. However, the benefits of novel activation funct…
From Prediction to Prescription: Evolutionary Optimization of Non-Pharmaceutical Interventions in the COVID-19 Pandemic
Risto Miikkulainen, Olivier Francon, Elliot Meyerson +3
Several models have been developed to predict how the COVID-19 pandemic spreads, and how it could be contained with non-pharmaceutical interventions (NPIs) such as social distancin…
Evolutionary Optimization of Deep Learning Activation Functions
Garrett Bingham, William Macke, Risto Miikkulainen
The choice of activation function can have a large effect on the performance of a neural network. While there have been some attempts to hand-engineer novel activation functions, t…
Adapting to Unseen Environments through Explicit Representation of Context
Cem C. Tutum, Risto Miikkulainen
In order to deploy autonomous agents to domains such as autonomous driving, infrastructure management, health care, and finance, they must be able to adapt safely to unseen situati…
Effective Reinforcement Learning through Evolutionary Surrogate-Assisted Prescription
Olivier Francon, Santiago Gonzalez, Babak Hodjat +4
There is now significant historical data available on decision making in organizations, consisting of the decision problem, what decisions were made, and how desirable the outcomes…
Regularized Evolutionary Population-Based Training
Jason Liang, Santiago Gonzalez, Hormoz Shahrzad +1
Metalearning of deep neural network (DNN) architectures and hyperparameters has become an increasingly important area of research. At the same time, network regularization has been…