Towards Searching Efficient and Accurate Neural Network Architectures in
Binary Classification Problems
- URL: http://arxiv.org/abs/2101.06511v1
- Date: Sat, 16 Jan 2021 20:00:38 GMT
- Title: Towards Searching Efficient and Accurate Neural Network Architectures in
Binary Classification Problems
- Authors: Yigit Alparslan, Ethan Jacob Moyer, Isamu Mclean Isozaki, Daniel
Schwartz, Adam Dunlop, Shesh Dave, Edward Kim
- Abstract summary: In this study, we optimize the selection process by investigating different search algorithms to find a neural network architecture size that yields the highest accuracy.
We apply binary search on a very well-defined binary classification network search space and compare the results to those of linear search.
We report a 100-fold running time improvement over the naive linear search when we apply the binary search method to our datasets.
- Score: 4.3871352596331255
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: In recent years, deep neural networks have had great success in machine
learning and pattern recognition. Architecture size for a neural network
contributes significantly to the success of any neural network. In this study,
we optimize the selection process by investigating different search algorithms
to find a neural network architecture size that yields the highest accuracy. We
apply binary search on a very well-defined binary classification network search
space and compare the results to those of linear search. We also propose how to
relax some of the assumptions regarding the dataset so that our solution can be
generalized to any binary classification problem. We report a 100-fold running
time improvement over the naive linear search when we apply the binary search
method to our datasets in order to find the best architecture candidate. By
finding the optimal architecture size for any binary classification problem
quickly, we hope that our research contributes to discovering intelligent
algorithms for optimizing architecture size selection in machine learning.
Related papers
- OFA$^2$: A Multi-Objective Perspective for the Once-for-All Neural
Architecture Search [79.36688444492405]
Once-for-All (OFA) is a Neural Architecture Search (NAS) framework designed to address the problem of searching efficient architectures for devices with different resources constraints.
We aim to give one step further in the search for efficiency by explicitly conceiving the search stage as a multi-objective optimization problem.
arXiv Detail & Related papers (2023-03-23T21:30:29Z) - Neural networks with linear threshold activations: structure and
algorithms [1.795561427808824]
We show that 2 hidden layers are necessary and sufficient to represent any function representable in the class.
We also give precise bounds on the sizes of the neural networks required to represent any function in the class.
We propose a new class of neural networks that we call shortcut linear threshold networks.
arXiv Detail & Related papers (2021-11-15T22:33:52Z) - Learning Structures for Deep Neural Networks [99.8331363309895]
We propose to adopt the efficient coding principle, rooted in information theory and developed in computational neuroscience.
We show that sparse coding can effectively maximize the entropy of the output signals.
Our experiments on a public image classification dataset demonstrate that using the structure learned from scratch by our proposed algorithm, one can achieve a classification accuracy comparable to the best expert-designed structure.
arXiv Detail & Related papers (2021-05-27T12:27:24Z) - Firefly Neural Architecture Descent: a General Approach for Growing
Neural Networks [50.684661759340145]
Firefly neural architecture descent is a general framework for progressively and dynamically growing neural networks.
We show that firefly descent can flexibly grow networks both wider and deeper, and can be applied to learn accurate but resource-efficient neural architectures.
In particular, it learns networks that are smaller in size but have higher average accuracy than those learned by the state-of-the-art methods.
arXiv Detail & Related papers (2021-02-17T04:47:18Z) - Evaluating Online and Offline Accuracy Traversal Algorithms for
k-Complete Neural Network Architectures [6.123324869194195]
In this paper, we study compact neural network architectures for binary classification.
We investigate improvements in speed and accuracy when favoring overcomplete architecture candidates.
arXiv Detail & Related papers (2021-01-16T20:37:29Z) - NAS-Navigator: Visual Steering for Explainable One-Shot Deep Neural
Network Synthesis [53.106414896248246]
We present a framework that allows analysts to effectively build the solution sub-graph space and guide the network search by injecting their domain knowledge.
Applying this technique in an iterative manner allows analysts to converge to the best performing neural network architecture for a given application.
arXiv Detail & Related papers (2020-09-28T01:48:45Z) - Disentangling Neural Architectures and Weights: A Case Study in
Supervised Classification [8.976788958300766]
This work investigates the problem of disentangling the role of the neural structure and its edge weights.
We show that well-trained architectures may not need any link-specific fine-tuning of the weights.
We use a novel and computationally efficient method that translates the hard architecture-search problem into a feasible optimization problem.
arXiv Detail & Related papers (2020-09-11T11:22:22Z) - VINNAS: Variational Inference-based Neural Network Architecture Search [2.685668802278155]
We present a differentiable variational inference-based NAS method for searching sparse convolutional neural networks.
Our method finds diverse network cells, while showing state-of-the-art accuracy with up to almost 2 times fewer non-zero parameters.
arXiv Detail & Related papers (2020-07-12T21:47:35Z) - DC-NAS: Divide-and-Conquer Neural Architecture Search [108.57785531758076]
We present a divide-and-conquer (DC) approach to effectively and efficiently search deep neural architectures.
We achieve a $75.1%$ top-1 accuracy on the ImageNet dataset, which is higher than that of state-of-the-art methods using the same search space.
arXiv Detail & Related papers (2020-05-29T09:02:16Z) - Binarizing MobileNet via Evolution-based Searching [66.94247681870125]
We propose a use of evolutionary search to facilitate the construction and training scheme when binarizing MobileNet.
Inspired by one-shot architecture search frameworks, we manipulate the idea of group convolution to design efficient 1-Bit Convolutional Neural Networks (CNNs)
Our objective is to come up with a tiny yet efficient binary neural architecture by exploring the best candidates of the group convolution.
arXiv Detail & Related papers (2020-05-13T13:25:51Z)
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.