The family of natural evolution strategies (NES) offers a principled approach to real-valued evolutionary optimization by following the natural gradient of the expected fitness. Like the well-known CMA-ES, the most competitive algorithm in the field, NES comes with important invariance properties. In this paper, we introduce a number of elegant and efficient improvements of the basic NES algorithm. First, we propose to parameterize the positive definite covariance matrix using the exponential map, which allows the covariance matrix to be updated in a vector space. This new technique makes the algorithm completely invariant under linear transformations of the underlying search space, which was previously achieved only in the limit of small step sizes. Second, we compute all updates in the natural coordinate system, such that the natural gradient coincides with the vanilla gradient. This way we avoid the computation of the inverse Fisher information matrix, which is the main computational bottleneck of the original NES algorithm. Our new algorithm, exponential NES (xNES), is significantly simpler than its predecessors. We show that the various update rules in CMA-ES are closely related to the natural gradient updates of xNES. However, xNES is more principled than CMA-ES, as all the update rules needed for covariance matrix adaptation are derived from a single principle. We empirically assess the performance of the new algorithm on standard benchmark functions.
Advances in machine learning (ML) and artificial intelligence (AI) present an opportunity to build better tools and solutions to help address some of the world's most pressing challenges, and deliver positive social impact in accordance with the priorities outlined in the United Nations' 17 Sustainable Development Goals (SDGs). The AI for Social Good (AI4SG) movement aims to establish interdisciplinary partnerships centred around AI applications towards SDGs. We provide a set of guidelines for establishing successful long-term collaborations between AI researchers and application-domain experts, relate them to existing AI4SG projects and identify key opportunities for future AI applications targeted towards social good. T he challenges facing our world today have grown in complexity and increasingly require large, coordinated efforts: between countries; and across a broad spectrum of governmental and non-governmental organisations (NGOs) and the communities they serve. These coordinated efforts work towards supporting the Sustainable Development Goals (SDGs) 1 , and there continues to be an important role for technology to support the developmental organisations and efforts active in this field to deliver the highest impact. Artificial intelligence (AI) and machine learning (ML) have attracted widespread interest in recent years due to a series of high-profile successes. AI has shown success in games and
The family of natural evolution strategies (NES) offers a principled approach to real-valued evolutionary optimization by following the natural gradient of the expected fitness on the parameters of its search distribution. While general in its formulation, existing research has focused only on multivariate Gaussian search distributions. We address this shortcoming by exhibiting problem classes for which other search distributions are more appropriate, and then derive the corresponding NES-variants.First, we show how simplifying NES to separable distributions reduces its complexity from O(d 3 ) to O(d), and apply it to problems of previously unattainable dimensionality, recovering lowest-energy structures on the Lennard-Jones atom clusters and state-of-the-art results on neuro-evolution benchmarks. Second, we develop a new, equivalent formulation based on invariances, which allows us to generalize NES to heavy-tailed distributions, even if their variance is undefined. We then investigate how this variant aids in overcoming deceptive local optima.
Objective. In electrophysiology, microelectrodes are the primary source for recording neural data (single unit activity). These microelectrodes can be implanted individually or in the form of arrays containing dozens to hundreds of channels. Recordings of some channels contain neural activity, which are often contaminated with noise. Another fraction of channels does not record any neural data, but only noise. By noise, we mean physiological activities unrelated to spiking, including technical artifacts and neural activities of neurons that are too far away from the electrode to be usefully processed. For further analysis, an automatic identification and continuous tracking of channels containing neural data is of great significance for many applications, e.g. automated selection of neural channels during online and offline spike sorting. Automated spike detection and sorting is also critical for online decoding in brain–computer interface (BCI) applications, in which only simple threshold crossing events are often considered for feature extraction. To our knowledge, there is no method that can universally and automatically identify channels containing neural data. In this study, we aim to identify and track channels containing neural data from implanted electrodes, automatically and more importantly universally. By universally, we mean across different recording technologies, different subjects and different brain areas. Approach. We propose a novel algorithm based on a new way of feature vector extraction and a deep learning method, which we call SpikeDeeptector. SpikeDeeptector considers a batch of waveforms to construct a single feature vector and enables contextual learning. The feature vectors are then fed to a deep learning method, which learns contextualized, temporal and spatial patterns, and classifies them as channels containing neural spike data or only noise. Main results. We trained the model of SpikeDeeptector on data recorded from a single tetraplegic patient with two Utah arrays implanted in different areas of the brain. The trained model was then evaluated on data collected from six epileptic patients implanted with depth electrodes, unseen data from the tetraplegic patient and data from another tetraplegic patient implanted with two Utah arrays. The cumulative evaluation accuracy was 97.20% on 1.56 million hand labeled test inputs. Significance. The results demonstrate that SpikeDeeptector generalizes not only to the new data, but also to different brain areas, subjects, and electrode types not used for training. Clinical trial registration number. The clinical trial registration number for patients implanted with the Utah array is NCT 01849822. For the epilepsy patients, approval from the local ethics committee at the Ruhr-University Bochum, Germany, was obtained prior to implantation.
Micromechanical modeling of material behavior has become an accepted approach to describe the macroscopic mechanical properties of polycrystalline materials in a microstructure-sensitive way. The microstructure is modeled by a representative volume element (RVE), and the anisotropic mechanical behavior of individual grains is described by a crystal plasticity model. Such micromechanical models are subjected to mechanical loads in a finite element (FE) simulation and their macroscopic behavior is obtained from a homogenization procedure. However, such micromechanical simulations with a discrete representation of the material microstructure are computationally very expensive, in particular when conducted for 3D models, such that it is prohibitive to apply them for process simulations of macroscopic components. In this work, we suggest a new approach to develop microstructure-sensitive, yet flexible and numerically efficient macroscopic material models by using micromechanical simulations for training Machine Learning (ML) algorithms to capture the mechanical response of various microstructures under different loads. In this way, the trained ML algorithms represent a new macroscopic constitutive relation, which is demonstrated here for the case of damage modeling. In a second application of the combination of ML algorithms and micromechanical modeling, a proof of concept is presented for the application of trained ML algorithms for microstructure design with respect to desired mechanical properties. The input data consist of different stress-strain curves obtained from micromechanical simulations of uniaxial testing of a wide range of microstructures. The trained ML algorithm is then used to suggest grain size distributions, grain morphologies and crystallographic textures, which yield the desired mechanical response for a given application. For validation purposes, the resulting grain microstructure parameters are used to generate RVEs, accordingly and the macroscopic stress-strain curves for those microstructures are calculated and compared with the target quantities. The two examples presented in this work, demonstrate clearly that ML methods can be trained by micromechanical simulations, which capture material behavior and its relation to Reimann et al. Application of Micromechanical Modeling on Machine Learningmicrostructural mechanisms in a physically sound way. Since the quality of the ML algorithms is only as good as that of the micromechanical model, it is essential to validate these models properly. Furthermore, this approach allows a hybridization of experimental and numerical data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.