Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts

Tian, Yingtao; Ha, David

doi:10.1007/978-3-031-03789-4_18

Cited by 17 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ing of an image, and this model is widely used in various kinds of downstream tasks [18,20,35,37,40,45]. We use CLIP for measuring visual similarities between images.…”

Section: C3 Similar-image-goal Localizationmentioning

confidence: 99%

Renderable Neural Radiance Map for Visual Navigation

Kwon¹,

Park²,

Oh³

2023

Preprint

View full text Add to dashboard Cite

We propose a novel type of map for visual navigation, a renderable neural radiance map (RNR-Map), which is designed to contain the overall visual information of a 3D environment. The RNR-Map has a grid form and consists of latent codes at each pixel. These latent codes are embedded from image observations, and can be converted to the neural radiance field which enables image rendering given a camera pose. The recorded latent codes implicitly contain visual information about the environment, which makes the RNR-Map visually descriptive. This visual information in RNR-Map can be a useful guideline for visual localization and navigation. We develop localization and navigation frameworks that can effectively utilize the RNR-Map. We evaluate the proposed frameworks on camera tracking, visual localization, and image-goal navigation. Experimental results show that the RNR-Map-based localization framework can find the target location based on a single query image with fast speed and competitive accuracy compared to other baselines. Also, this localization framework is robust to environmental changes, and even finds the most visually similar places when a query image from a different environment is given. The proposed navigation framework outperforms the existing image-goal navigation methods in difficult scenarios, under odometry and actuation noises. The navigation framework shows 65.7% success rate in curved scenarios of the NRNS [23] dataset, which is an improvement of 18.6% over the current state-of-the-art. Project page: https: //rllab-snu.github.io/projects/RNR-Map/

show abstract

“…ing of an image, and this model is widely used in various kinds of downstream tasks [18,20,35,37,40,45]. We use CLIP for measuring visual similarities between images.…”

Section: C3 Similar-image-goal Localizationmentioning

confidence: 99%

Renderable Neural Radiance Map for Visual Navigation

Kwon¹,

Park²,

Oh³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…• We employ our novel implementation of EFP in various experiments including neural network learning and image synthesis (Tian and Ha, 2022).…”

Section: Our Contributionsmentioning

confidence: 99%

“…We also consider the image synthesis experiment in Tian and Ha (2022), where the goal is to "approximate" an image via integrating transparent triangles. To draw the triangles, we utilize a differentiable render (Laine et al, 2020) that provides a differentiable map to translate the parameters θ (representing the colors and vertexes) into a transparent triangle h(θ).…”

Section: Image Synthesis With Trianglesmentioning

confidence: 99%

Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems

Nitanda¹,

Oko²,

Wu³

et al. 2023

Preprint

View full text Add to dashboard Cite

The entropic fictitious play (EFP) is a recently proposed algorithm that minimizes the sum of a convex functional and entropy in the space of measures -such an objective naturally arises in the optimization of a two-layer neural network in the mean-field regime. In this work, we provide a concise primal-dual analysis of EFP in the setting where the learning problem exhibits a finite-sum structure. We establish quantitative global convergence guarantees for both the continuous-time and discrete-time dynamics based on properties of a proximal Gibbs measure introduced in Nitanda et al. ( 2022). Furthermore, our primal-dual framework entails a memory-efficient particle-based implementation of the EFP update, and also suggests a connection to gradient boosting methods. We illustrate the efficiency of our novel implementation in experiments including neural network optimization and image synthesis.

show abstract

“…The ML functional is trained using a bioinspired nongradient-based approach adapted from particle swarm optimization (PSO). 52 This class of optimization algorithms have shown success in handling intricate nonlinear loss functions 53 owing to the collective intelligence ingredient that improves the efficiency of the optimization process. These results show that by training a correction over r2SCAN using three light molecules and three diatomic (metal-nonmetal) transition molecules, the prediction of adiabatic energy differences is improved compared to that of the state-of-theart in approximate KS-DFT at no expenses for the performance on atomization energies.…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Network-Based Density Functional Approach for Adiabatic Energy Differences in Transition Metal Complexes

de Mendonça,

Mariano,

Devijver

et al. 2023

J. Chem. Theory Comput.

View full text Add to dashboard Cite

During the past decades, approximate Kohn−Sham density functional theory schemes have garnered many successes in computational chemistry and physics, yet the performance in the prediction of spin state energetics is often unsatisfactory. By means of a machine learning approach, an enhanced exchange and correlation functional is developed to describe adiabatic energy differences in transition metal complexes. The functional is based on the computationally efficient revision of the regularized, strongly constrained, and appropriately normed functional and improved by an artificial neural network correction trained over a small data set of electronic densities, atomization energies, and/or spin state energetics. The training process, performed using a bioinspired nongradient-based approach adapted for this work from the particle swarm optimization, is analyzed and discussed extensively. The resulting machine learned meta-generalized gradient approximation functional is shown to outperform most known density functionals in the prediction of adiabatic energy differences for a diverse set of transition metal complexes with varying local coordinations and metal choices.

show abstract

Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts

Cited by 17 publications

References 23 publications

Renderable Neural Radiance Map for Visual Navigation

Renderable Neural Radiance Map for Visual Navigation

Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems

Artificial Neural Network-Based Density Functional Approach for Adiabatic Energy Differences in Transition Metal Complexes

Contact Info

Product

Resources

About