Search Results for author:
Found 52 papers, 13 papers with code
Characterizing Dynamic Word Meaning Representations in the Brain
During sentence comprehension, humans adjust word meanings according to the combination of the concepts that occur in the sentence.
Understanding the Semantic Space: How Word Meanings Dynamically Adapt in the Context of a Sentence
How do people understand the meaning of the word “small” when used to describe a mosquito, a church, or a planet?
Accelerating Evolution Through Gene Masking and Distributed Search
In building practical applications of evolutionary computation (EC), two optimizations are essential.
Efficient Activation Function Optimization through Surrogate Modeling
Carefully designed activation functions can improve the performance of neural networks in many machine learning tasks.
Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search
This paper presents the first theoretical analysis of the behaviors of mutation, crossover and RL in black-box NAS, and proposes a new crossover operator based on the shortest edit path (SEP) in graph space.
EVOTER: Evolution of Transparent Explainable Rule-sets
The approach is evaluated in several prediction/classification and prescription/policy search domains with and without a surrogate.
Effective Mutation Rate Adaptation through Group Elite Selection
GESMR co-evolves a population of solutions and a population of MRs, such that each MR is assigned to a group of solutions.
DIAS: A Domain-Independent Alife-Based Problem-Solving System
A domain-independent problem-solving system based on principles of Artificial Life is introduced.
Simple Genetic Operators are Universal Approximators of Probability Distributions (and other Advantages of Expressive Encodings)
The conclusion is that, across evolutionary computation areas as diverse as genetic programming, neuroevolution, genetic algorithms, and theory, expressive encodings can be a key to understanding and realizing the full power of evolution.
NeuroComb: Improving SAT Solving with Graph Neural Networks
Aiming to make GNN improvements practical, this paper proposes an approach called NeuroComb, which builds on two insights: (1) predictions of important variables and clauses can be combined with dynamic branching into a more effective hybrid branching strategy, and (2) it is sufficient to query the neural model only once for the predictions before the SAT solving starts.
AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks
By analytically tracking the mean and variance of signals as they propagate through the network, AutoInit appropriately scales the weights at each layer to avoid exploding or vanishing signals.
Evolving GAN Formulations for Higher Quality Image Synthesis
Generative Adversarial Networks (GANs) have extended deep learning to complex generation and translation tasks across different data modalities.
The Traveling Observer Model: Multi-task Learning Through Spatial Variable Embeddings
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.
Detecting Misclassification Errors in Neural Networks with a Gaussian Process Model
This framework, RED, builds an error detector on top of the base classifier and estimates uncertainty of the detection scores using Gaussian Processes.
Effective Regularization Through Loss-Function Metalearning
Evolutionary optimization, such as the TaylorGLO method, can be used to discover novel, customized loss functions for deep neural networks, resulting in improved performance, faster training, and improved data utilization.
Creative AI Through Evolutionary Computation: Principles and Examples
The main power of artificial intelligence is not in modeling what we already know, but in creating solutions that are new.
Generalization of Agent Behavior through Explicit Representation of Context
In order to deploy autonomous agents in digital interactive environments, they must be able to act robustly in unseen situations.
Discovering Parametric Activation Functions
Recent studies have shown that the choice of activation function can significantly affect the performance of deep learning networks.
From Prediction to Prescription: Evolutionary Optimization of Non-Pharmaceutical Interventions in the COVID-19 Pandemic
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 distancing restrictions and school and business closures.
Evolutionary Optimization of Deep Learning Activation Functions
The choice of activation function can have a large effect on the performance of a neural network.
Adapting to Unseen Environments through Explicit Representation of Context
This paper proposes a principled approach where a context module is coevolved with a skill module.
Effective Reinforcement Learning through Evolutionary Surrogate-Assisted Prescription
Using this data, it is possible to learn a surrogate model, and with that model, evolve a decision strategy that optimizes the outcomes.
Regularized Evolutionary Population-Based Training
This paper presents an algorithm called Evolutionary Population-Based Training (EPBT) that interleaves the training of a DNN's weights with the metalearning of loss functions.
MDEA: Malware Detection with Evolutionary Adversarial Learning
Malware detection have used machine learning to detect malware in programs.
Improving Neural Network Learning Through Dual Variable Learning Rates
This paper introduces and evaluates a novel training method for neural networks: Dual Variable Learning Rates (DVLR).
Optimizing Loss Functions Through Multivariate Taylor Polynomial Parameterization
Metalearning of deep neural network (DNN) architectures and hyperparameters has become an increasingly important area of research.
Improved Training Speed, Accuracy, and Data Utilization via Loss Function Optimization
As the complexity of neural network models has grown, it has become increasingly important to optimize their design automatically through metalearning.
Enhanced Optimization with Composite Objectives and Novelty Pulsation
This paper improves this approach further by introducing novelty pulsation, i. e. a systematic method to alternate between novelty selection and local optimization.
Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernel
In many such tasks, the point prediction is not enough: the uncertainty (i. e. risk or confidence) of that prediction must also be estimated.
Modular Universal Reparameterization: Deep Multi-task Learning Across Diverse Domains
As deep learning applications continue to become more diverse, an interesting question arises: Can general problem solving arise from jointly learning several such diverse tasks?
Better Future through AI: Avoiding Pitfalls and Guiding AI Towards its Full Potential
Artificial Intelligence (AI) technology is rapidly changing many areas of society.
Improved Training Speed, Accuracy, and Data Utilization Through Loss Function Optimization
As the complexity of neural network models has grown, it has become increasingly important to optimize their design automatically through metalearning.
Ranked #44 on
Image Classification
on MNIST
Functional Generative Design of Mechanisms with Recurrent Neural Networks and Novelty Search
However, while static designs are easily produced with 3D printing, functional designs with moving parts are more difficult to generate: The search space is too high-dimensional, the resolution of the 3D-printed parts is not adequate, and it is difficult to predict the physical behavior of imperfect 3D-printed mechanisms.
Evolutionary Neural AutoML for Deep Learning
However, the success of DNNs depends on the proper configuration of its architecture and hyperparameters.
Creative AI Through Evolutionary Computation
The main power of artificial intelligence is not in modeling what we already know, but in creating solutions that are new.
Faster Training by Selecting Samples Using Embeddings
Long training times have increasingly become a burden for researchers by slowing down the pace of innovation, with some models taking days or weeks to train.
A Comparison of the Taguchi Method and Evolutionary Optimization in Multivariate Testing
Its performance is compared to that of the Taguchi method in several simulated conditions, including an orthogonal one designed to favor the Taguchi method, and two realistic conditions with dependences between variables.
Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing—and Back
Deep multitask learning boosts performance by sharing learned structure across related tasks.
Functional Generative Design: An Evolutionary Approach to 3D-Printing
The proposed methodology for discovering solutions to this problem consists of three components: First, an effective search space is learned through a variational autoencoder (VAE); second, a surrogate model for functional designs is built; and third, a genetic algorithm is used to simultaneously update the hyperparameters of the surrogate and to optimize the designs using the updated surrogate.
From Nodes to Networks: Evolving Recurrent Neural Networks
Gated recurrent networks such as those composed of Long Short-Term Memory (LSTM) nodes have recently been used to improve state of the art in many sequential processing tasks such as speech recognition and machine translation.
Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing---and Back
Deep multitask learning boosts performance by sharing learned structure across related tasks.
Enhanced Optimization with Composite Objectives and Novelty Selection
An important benefit of multi-objective search is that it maintains a diverse population of candidates, which helps in deceptive problems in particular.
Enhancing Evolutionary Conversion Rate Optimization via Multi-armed Bandit Algorithms
Traffic is allocated to candidate solutions using a multi-armed bandit algorithm, using more traffic on those evaluations that are most useful.
Evolutionary Architecture Search For Deep Multitask Networks
Multitask learning, i. e. learning several tasks at once with the same neural network, can improve performance in each of the tasks.
The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them.
Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering
Existing deep multitask learning (MTL) approaches align layers shared between tasks in a parallel ordering.
Discovering Evolutionary Stepping Stones through Behavior Domination
The conclusion is that behavior domination can help illuminate the complex dynamics of behavior-driven search, and can thus lead to the design of more scalable and robust algorithms.
Conversion Rate Optimization through Evolutionary Computation
Conversion optimization means designing a web interface so that as many users as possible take a desired action on it, such as register or purchase.
Evolving Deep Neural Networks
The success of deep learning depends on finding an architecture to fit the task.
Reuse of Neural Modules for General Video Game Playing
A general approach to knowledge transfer is introduced in which an agent controlled by a neural network adapts how it reuses existing networks as it learns in a new domain.
Increasing Behavioral Complexity for Evolved Virtual Creatures with the ESP Method
Since their introduction in 1994 (Sims), evolved virtual creatures (EVCs) have employed the coevolution of morphology and control to produce high-impact work in multiple fields, including graphics, evolutionary computation, robotics, and artificial life.
Evolving Neural Networks through Augmenting Topologies
An important question in neuroevolution is how to gain an advantage from evolving neural network topologies along with weights.
