Deep learning improves evolutionary algorithms' adaptability.
problem Improving evolutionary algorithms' adaptability to various circumstances.
method Using deep reinforcement learning to dynamically adjust evolutionary algorithms' strategies.
result Deep learning enhances evolutionary algorithms' fitness increase and attainable fitness.
A method uses evolutionary algorithm to supervise unsupervised learning in deep neural networks.
problem Controlling unsupervised learning in deep neural networks.
method Evolutionary algorithm applied to deep neural networks for supervised unsupervised learning.
result Better accuracy in document classification compared to traditional methods.
Paper withdrawn; AI game behavior needs diversity.
problem Creating varied human-like playing styles in games.
method Evolutionary multi-objective deep reinforcement learning.
result Generated diverse AI behaviors for games.
Improves sample efficiency in evolutionary policy search methods.
problem Worse sample efficiency in evolutionary policy search methods.
method Importance mixing to reuse more samples.
result Improves sample efficiency but still less than deep reinforcement learning.
Deep learning quantifies butterfly phenotypes, validating evolutionary theory.
problem Capturing comprehensive phenotypic information of butterflies.
method Deep convolutional triplet network for phenotypic distance calculation.
result Euclidean phenotypic distances support classical mimicry theory.
Evo-NAS combines neural and evolutionary methods for efficient neural architecture search.
problem Efficiently searching for optimal neural architectures in deep learning.
method Evolutionary-Neural hybrid agents that combine the strengths of neural and evolutionary algorithms.
result Evo-NAS outperforms both neural and evolutionary agents in architecture search for various classification tasks.
Study uses evolutionary deep learning to identify galaxies obscured by star densities.
problem Identifying galaxies in the Zone of Avoidance due to high star densities and extinction.
method Evolutionary algorithm to optimize CNN architecture for near-infrared images.
result Best evolved CNN outperforms other variants in identifying galaxies in the Zone of Avoidance.
Evolutionary algorithm improves DNN watermarking with fewer false positives.
problem Protecting deep learning models from piracy and proving ownership.
method Evolutionary algorithm for generating and optimizing trigger patterns.
result Reduces false positive rates in DNN watermarking.
This paper reviews the history and development of deep learning models.
problem Understanding the evolution and development of deep learning models.
method Review of historical models and their evolutionary paths.
result Summarizes the development and evolution of deep learning models.
DO uses DNNs to solve combinatorial optimisation problems.
problem Solving complex combinatorial optimisation problems.
method Combines evolutionary search with DNNs to learn and exploit problem structure.
result DO can solve problems like HTOP and MCparity that other algorithms cannot.
EDEN evolves efficient neural networks for machine learning.
problem Increasing complexity of deep neural networks requires better guidance for architecture and hyperparameter selection.
method EDEN uses neuro-evolution to evolve simple yet successful architectures from basic layers and hyperparameters.
result EDEN reliably finds good networks, achieving state-of-the-art results on multiple datasets in a short time.
Evolutionary algorithms improve neural network performance by discovering better activation functions.
problem The choice of activation function affects neural network performance, but ReLU remains dominant.
method Defined a tree-based search space of candidate activation functions and used evolutionary algorithms (mutation, crossover, exhaustive search) to explore and discover better functions.
result Replacing ReLU with evolved activation functions statistically significantly increases network accuracy.
LR-EDNN reduces PDE solver complexity by limiting network weights to low-rank subspace.
problem Efficiently solving time-dependent PDEs with deep neural networks.
method Low-rank constraint on network weights using SVD for efficient parameter updates.
result LR-EDNN achieves comparable accuracy to full EDNN with fewer parameters and lower cost.
ESGD optimizes deep neural networks using evolutionary and stochastic gradient descent methods.
problem Optimizing deep neural networks efficiently and effectively.
method Combines SGD and evolutionary algorithms, alternating between steps to improve population fitness.
result Guarantees that the best fitness in the population never degrades and optimizes across various deep architectures.
API identifies regression or classification problems with high accuracy.
problem Automatically identifying regression or classification problems.
method Evolutionary Deep Learning (EDL) algorithm using TensorFlow.
result API achieves 96.3% accuracy in identifying problem types.
A real-time federated neural architecture search approach reduces costs and improves performance.
problem High communication and computational demands in federated learning for large models.
method Evolutionary approach with double-sampling technique to optimize model performance and reduce costs.
result Effective real-time federated neural architecture search for deep models on edge devices.
Parameter noise enhances RL exploration efficiency.
problem Enhancing RL exploration efficiency through parameter noise.
method Combining parameter noise with traditional RL methods.
result RL with parameter noise learns more efficiently than traditional RL methods.
Combines evolutionary and RL methods for better policy search.
problem Low sample efficiency in evolutionary methods and high sensitivity in RL methods.
method Combines CEM and td3 algorithms for policy search.
result cem-rl offers a better trade-off between performance and sample efficiency.
PDERL improves evolutionary reinforcement learning by using learning-based variation operators.
problem Scalability issue in Genetic Algorithms when combined with Deep Neural Networks.
method Integrates evolutionary and reinforcement learning through a hierarchical approach with learning-based variation operators.
result PDERL outperforms traditional evolutionary and reinforcement learning methods in robot locomotion tasks.
Synthetic neural networks with fewer connections perform better.
problem Creating highly efficient deep neural networks.
method Synaptic cluster-driven genetic encoding mimics biological evolution.
result Synthetic networks achieve state-of-the-art performance with significantly fewer connections.
GADAM uses genetic algorithm to improve Adam's performance in deep learning.
problem Deep learning optimization stuck in local optima.
method GADAM combines Adam and genetic algorithm to evolve unit models.
result GADAM effectively avoids local optima and achieves faster convergence.
GEN Model uses genetic-evolutionary strategy for deep learning.
problem Deep learning models are complex and hard to interpret.
method GEN Model builds a group of unit models through genetic-evolutionary learning.
result GEN Model outperforms state-of-the-art methods in effectiveness and efficiency.
New method shows cultural transmission improves language compositionality.
problem How cultural transmission affects language emergence and compositionality.
method Introduced cultural evolutionary dynamics into language emergence by periodically replacing agents in a population.
result Languages emerge with better compositional generalization due to implicit cultural transmission.
High-frequency trading models fail due to overfitting and survivor bias.
problem Failure of hybrid DRL-EC trading systems in high-frequency environments.
method Deployed a population of 500 agents in a high-frequency cryptocurrency environment, analyzing failure modes through multi-disciplinary lens.
result Increasing model complexity without information asymmetry exacerbates systemic fragility.
EA-LSTM improves LSTM for time series prediction by evolving attention.
problem LSTMs struggle with assigning varying attention to sub-windows in time series data.
method Evolutionary attention-based LSTM with competitive random search.
result EA-LSTM achieves competitive performance in multivariate time series prediction.
New back-propagation rules discovered through evolutionary methods.
problem Improving the back-propagation algorithm for faster training.
method Evolutionary approach to discover new update equations.
result Several new update equations that train faster and perform similarly at convergence.
A hybrid method improves Convolutional Neural Networks training.
problem Training Convolutional Neural Networks efficiently and avoiding local minima.
method Combines backpropagation with evolutionary strategies.
result Improves accuracy by 0.61% on CIFAR-10 image classification.
Automatically discovers effective activation functions for deep learning.
problem Inconsistent performance of novel activation functions in deep learning networks.
method Evolutionary search for general form, gradient descent for parameters.
result Significant performance improvements over ReLU and other functions.
Trading strategies evolve in a simulated market to outperform real data.
problem Creating profitable trading strategies in diverse market conditions.
method Agent-based model of heterogeneous agents evolving deep neural networks.
result Elite trading algorithms outperform in real high-frequency foreign exchange data.
Survey of neural architecture search methods.
problem Automating the selection of neural network architectures.
method Comprehensive analysis of existing methods using reinforcement learning, evolutionary algorithms, and surrogate models.
result Unified formalism for categorizing and comparing architecture search methods.
Paper improves deep learning for solving evolutionary equations with trainable hard constraints.
problem Low computational accuracy of standard PINNs in large temporal domains.
method Sequential learning strategies and trainable influence functions for hard constraints.
result Significantly improved computational accuracy and universality of the method.
OpEvo automates tensor operator optimization for better efficiency.
problem Manual optimization of tensor operators is inefficient and limited.
method OpEvo uses evolutionary computation with topology-aware mutation.
result OpEvo finds optimal configurations with less effort and variance.
Robotic grasping improved using evolutionary computing and deep reinforcement learning.
problem Developing a robot capable of grasping objects as skillfully as humans.
method Position estimation using Genetic Algorithm and regression, orientation learning using deep reinforcement learning.
result Deep reinforcement learning model outperforms traditional methods for orientation learning.
Combines variational and evolutionary optimization for generative models.
problem Optimizing generative models with discrete latent variables.
method Truncated posteriors as variational distributions, evolutionary algorithms applied to variational parameters.
result Evolutionary algorithms effectively optimize variational bounds for generative models.
Automates design of lightweight neural networks for image classification.
problem Designing efficient neural networks for edge devices with limited computational resources.
method Uses the Mesh Adaptive Direct Search (MADS) algorithm to optimize network architecture.
result Achieves comparable performance to standard methods with fewer design trials.
Ansor generates high-performance tensor programs for deep learning.
problem Generating high-performance tensor programs for deep learning on various hardware platforms is challenging.
method Ansor uses a hierarchical representation of the search space, sampling programs, and evolutionary search with a learned cost model to find high-performance programs.
result Ansor improves deep neural network execution performance up to 3.8x on Intel CPU, 2.6x on ARM CPU, and 1.7x on NVIDIA GPU.
Evolutionary method constructs CNNs for data compression and classification.
problem Creating efficient CNNs for data compression and classification.
method Two-step approach using evolutionary algorithms: 1) Convolutional autoencoder, 2) Convolutional neural network. Compression trade-off considered.
result Framework achieves comparable accuracy to hand-crafted networks, demonstrating effectiveness.
ERL combines evolutionary algorithms with reinforcement learning to improve control tasks.
problem Challenges in reinforcement learning, including sparse rewards, lack of exploration, and sensitivity to hyperparameters.
method ERL integrates evolutionary algorithms with reinforcement learning, using an EA's diversity and gradient information to enhance RL's performance.
result ERL significantly outperforms prior reinforcement learning and evolutionary algorithms in challenging control tasks.
New bound for neural nets on non-iid data.
problem Generalization of deep nets for dependent data.
method Establishes a generalization bound for feed-forward neural networks on φ-mixing data. result Proves neural nets can generalize well on non-iid data.
Taking inspiration from biological evolution, we explore the idea of "Can deep neural networks evolve naturally over successive generations into highly efficient deep neural networks?" by introducing the notion of synthesizing new highly efficient, yet powerful deep neural networks over successive generations via an ev…
evo-RL combines evolutionary computation with reinforcement learning for better adaptability.
problem Improving reinforcement learning algorithms' adaptability and performance in environments with rewardless states.
method Embedding reinforcement learning in an evolutionary cycle, distinguishing instinctive from learnable behavior.
result evo-RL leads to state-of-the-art performance on OpenAI Gym control problems with rewardless states.
BoGA combines evolutionary search with Bayesian optimization for efficient protein design.
problem Designing novel proteins with specific characteristics is challenging due to sequence space complexity.
method BoGA integrates a genetic algorithm with Bayesian optimization to efficiently explore sequence space.
result BoGA accelerates discovery of high-confidence binders for diverse protein design objectives.
DHRL learns interpretable features from visual data.
problem Limited use of deep learning in basic research for interpretable features.
method Generative model chaining, ladder network architecture, latent space regularization.
result DHRL generates disentangled hierarchical features from small datasets.
Optimizes master faces for 2D and 3D face verification using evolutionary algorithms and neural networks.
problem Impersonation attacks using master faces for face-based identity authentication.
method Evolutionary algorithm in latent space of StyleGAN, neural network to direct search, 2D and 3D face reconstruction.
result Obtains high impersonation rates with fewer master faces for 2D and 3D face verification.
Momentum speeds up evolutionary processes in machine learning.
problem Accelerating convergence in evolutionary dynamics.
method Combining momentum from machine learning with evolutionary dynamics using information divergences as Lyapunov functions.
result Momentum accelerates convergence of evolutionary dynamics, including the replicator equation and Euclidean gradient descent.
This paper proposes AI-based solutions for optimizing semiconductor manufacturing processes.
problem Optimizing semiconductor manufacturing processes with advanced analytics.
method Evolutionary Computing and Deep Learning algorithms for feature selection and neural networks.
result Advanced algorithm for intelligent feature selection in semiconductor manufacturing.
BEKAN uses RBFs and evolutionary methods to solve PDEs with boundary conditions.
problem Enforcing boundary conditions in neural networks for PDE solutions.
method Boundary condition-guaranteed evolutionary Kolmogorov-Arnold Network (BEKAN) with radial basis functions (RBFs). Incorporates Dirichlet, periodic, and Neumann conditions.
result BEKAN outperforms MLP and B-splines KAN in solving PDEs with boundary conditions.
PhyloVAE learns tree topologies without supervision.
problem Learning accurate tree representations from evolutionary data.
method Unsupervised learning via variational autoencoders with efficient tree generation.
result PhyloVAE generates high-resolution tree topologies efficiently.