High-performance Evolutionary Algorithms for Online Neuron Control

• URL: http://arxiv.org/abs/2204.06765v1
• Date: Thu, 14 Apr 2022 05:49:04 GMT
• Title: High-performance Evolutionary Algorithms for Online Neuron Control
• Authors: Binxu Wang, Carlos R. Ponce
• Abstract summary: In the visual system, neurons respond to images with graded and noisy responses. We have used black-box searches to search a 4096d image space, leading to the evolution of images that maximize neuronal responses.
• Score: 7.6146285961466
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recently, optimization has become an emerging tool for neuroscientists to study neural code. In the visual system, neurons respond to images with graded and noisy responses. Image patterns eliciting highest responses are diagnostic of the coding content of the neuron. To find these patterns, we have used black-box optimizers to search a 4096d image space, leading to the evolution of images that maximize neuronal responses. Although genetic algorithm (GA) has been commonly used, there haven't been any systematic investigations to reveal the best performing optimizer or the underlying principles necessary to improve them. Here, we conducted a large scale in silico benchmark of optimizers for activation maximization and found that Covariance Matrix Adaptation (CMA) excelled in its achieved activation. We compared CMA against GA and found that CMA surpassed the maximal activation of GA by 66% in silico and 44% in vivo. We analyzed the structure of Evolution trajectories and found that the key to success was not covariance matrix adaptation, but local search towards informative dimensions and an effective step size decay. Guided by these principles and the geometry of the image manifold, we developed SphereCMA optimizer which competed well against CMA, proving the validity of the identified principles. Code available at https://github.com/Animadversio/ActMax-Optimizer-Dev

Related papers

• Enhancing Skin Cancer Diagnosis (SCD) Using Late Discrete Wavelet Transform (DWT) and New Swarm-Based Optimizers [0.0]
  Skin cancer stands out as one of the most life-threatening forms of cancer, with its danger amplified if not diagnosed and treated promptly. Deep Learning has emerged as a powerful tool in the early detection and skin cancer diagnosis (SCD) This paper proposes a novel approach to skin cancer detection, utilizing optimization techniques in conjunction with pre-trained networks and wavelet transformations.
  arXiv  Detail & Related papers  (2024-11-30T13:17:52Z)
• Enhancing Brain Tumor Classification Using TrAdaBoost and Multi-Classifier Deep Learning Approaches [0.0]
  Brain tumors pose a serious health threat due to their rapid growth and potential for metastasis. This study aims to improve the efficiency and accuracy of brain tumor classification. Our approach combines state-of-the-art deep learning algorithms, including the Vision Transformer (ViT), Capsule Neural Network (CapsNet), and convolutional neural networks (CNNs) such as ResNet-152 and VGG16.
  arXiv  Detail & Related papers  (2024-10-31T07:28:06Z)
• Tumoral Angiogenic Optimizer: A new bio-inspired based metaheuristic [5.013833066304755]
  We propose a new metaheuristic inspired by the morphogenetic cellular movements of endothelial cells (ECs) that occur during the tumor angiogenesis process. The proposed algorithm is applied to real-world problems (cantilever beam design, pressure vessel design, tension/compression spring and sustainable explotation renewable resource)
  arXiv  Detail & Related papers  (2023-09-12T03:51:53Z)
• Convolutional Neural Generative Coding: Scaling Predictive Coding to Natural Images [79.07468367923619]
  We develop convolutional neural generative coding (Conv-NGC) We implement a flexible neurobiologically-motivated algorithm that progressively refines latent state maps. We study the effectiveness of our brain-inspired neural system on the tasks of reconstruction and image denoising.
  arXiv  Detail & Related papers  (2022-11-22T06:42:41Z)
• An Empirical Evaluation of Zeroth-Order Optimization Methods on AI-driven Molecule Optimization [78.36413169647408]
  We study the effectiveness of various ZO optimization methods for optimizing molecular objectives. We show the advantages of ZO sign-based gradient descent (ZO-signGD) We demonstrate the potential effectiveness of ZO optimization methods on widely used benchmark tasks from the Guacamol suite.
  arXiv  Detail & Related papers  (2022-10-27T01:58:10Z)
• An Improved Deep Convolutional Neural Network by Using Hybrid Optimization Algorithms to Detect and Classify Brain Tumor Using Augmented MRI Images [0.9990687944474739]
  In this paper, an improvement in deep convolutional learning is ensured by adopting enhanced optimization algorithms. Experimental studies are conducted to validate the performance of the suggested method on a total number of 2073 augmented MRI images. The performance comparison shows that the DCNN-G-HHO is much more successful than existing methods, especially on a scoring accuracy of 97%.
  arXiv  Detail & Related papers  (2022-06-08T14:29:06Z)
• Effective Mutation Rate Adaptation through Group Elite Selection [50.88204196504888]
  This paper introduces the Group Elite Selection of Mutation Rates (GESMR) algorithm. GESMR co-evolves a population of solutions and a population of MRs, such that each MR is assigned to a group of solutions. With the same number of function evaluations and with almost no overhead, GESMR converges faster and to better solutions than previous approaches.
  arXiv  Detail & Related papers  (2022-04-11T01:08:26Z)
• Improving RNA Secondary Structure Design using Deep Reinforcement Learning [69.63971634605797]
  We propose a new benchmark of applying reinforcement learning to RNA sequence design, in which the objective function is defined to be the free energy in the sequence's secondary structure. We show results of the ablation analysis that we do for these algorithms, as well as graphs indicating the algorithm's performance across batches.
  arXiv  Detail & Related papers  (2021-11-05T02:54:06Z)
• Segmentation of Brain MRI using an Altruistic Harris Hawks' Optimization algorithm [29.895517914678816]
  An efficient segmentation of brain Magnetic Resonance Images (MRIs) is of prime concern to radiologists. Thresholding is a popular method for segmentation that uses the histogram of an image to label different homogeneous groups of pixels into different classes. In this paper, we perform the multi-level thresholding using an evolutionary metaheuristic.
  arXiv  Detail & Related papers  (2021-09-17T17:51:34Z)
• Fused Deep Features Based Classification Framework for COVID-19 Classification with Optimized MLP [0.0]
  The new type of Coronavirus disease called COVID-19 continues to spread quite rapidly. Although it shows some specific symptoms, this disease, which can show different symptoms in almost every individual, has caused hundreds of thousands of patients to die. The help of computer aided diagnosis (CAD) and artificial intelligence (AI) algorithms is vital.
  arXiv  Detail & Related papers  (2021-03-15T14:30:12Z)
• Comparisons among different stochastic selection of activation layers for convolutional neural networks for healthcare [77.99636165307996]
  We classify biomedical images using ensembles of neural networks. We select our activations among the following ones: ReLU, leaky ReLU, Parametric ReLU, ELU, Adaptive Piecewice Linear Unit, S-Shaped ReLU, Swish, Mish, Mexican Linear Unit, Parametric Deformable Linear Unit, Soft Root Sign.
  arXiv  Detail & Related papers  (2020-11-24T01:53:39Z)
• AdaLead: A simple and robust adaptive greedy search algorithm for sequence design [55.41644538483948]
  We develop an easy-to-directed, scalable, and robust evolutionary greedy algorithm (AdaLead) AdaLead is a remarkably strong benchmark that out-competes more complex state of the art approaches in a variety of biologically motivated sequence design challenges.
  arXiv  Detail & Related papers  (2020-10-05T16:40:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.