This article presents the first results from using a learning classifier system capable of performing adaptive computation with deep neural networks. Individual classifiers within the population are composed of two neural networks. The first acts as a gating or guarding component, which enables the conditional computation of an associated deep neural network on a per instance basis. Self-adaptive mutation is applied upon reproduction and prediction networks are refined with stochastic gradient descent during lifetime learning. The use of fully-connected and convolutional layers are evaluated on handwritten digit recognition tasks where evolution adapts (i) the gradient descent learning rate applied to each layer (ii) the number of units within each layer, i.e., the number of fully-connected neurons and the number of convolutional kernel filters (iii) the connectivity of each layer, i.e., whether each weight is active (iv) the weight magnitudes, enabling escape from local optima. The system automatically reduces the number of weights and units while maintaining performance after achieving a maximum prediction error.
An investigation into the performances of the Current state-of-the-art Naive Bayes, Non-Bayesian and Deep Learning Based Classifier for Phishing Detection: A Survey
The University of Texas at El Paso(德克萨斯大学埃尔帕索分校);Office of Naval Research(海军研究办公室);Palo Alto Networks Inc(帕洛阿尔托网络公司)
HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual Recognition
University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Carnegie Mellon University(卡内基梅隆大学);eBay Research Lab(eBay研究实验室);The University of Hong Kong(香港大学)
On the Choice of General Purpose Classifiers in Learned Bloom Filters: An Initial Analysis Within Basic Filters
Università degli Studi di Milano(米兰大学);Università di Palermo(巴勒莫大学);CINI National Laboratory in Artificial Intelligence and Intelligent Systems (AIIS), Università di Roma(罗马大学 CINI 人工智能与智能系统国家实验室)