Connectionist Learning Classifier System
نویسنده
چکیده
Impetuous development of artificial neural networks makes it possible to transfer many ideas from this area into adjacent areas. This work investigates an opportunity of mapping learning classifier systems (LCS) into artificial neural networks (ANN). Possible learning types for hybrid connectionist classifier system (CLCS) for multi-step problems are derived. Transformation’s opportunity of the existing LCS into CLCS is shown. Heuristic LCS and CLCS comparisons in the dynamic environment show superiority of CLCS over LCS.
منابع مشابه
Autonomous Agent Control Using Connectionist Xcs Classifier System
In this paper a new connectionist classifier system CXCS is proposed, which uses a layer of competitive artificial neurons for decision making. New algorithms of the CXCS learning in multi-step problems are developed, where the correct result becomes known only at a certain system's step. CXCS is employed to control an autonomous agent in discrete environments.
متن کاملLearning Classifier Systems
Learning Classifier Systems are a machine learning technique that may be categorised in between symbolic production systems and sub-symbolic connectionist systems. Classifiers are cognitive paradigm for adaptation that learn in environments of perpetual novelty with minimal and delayed reward. They employ two principle processes (1) reinforcement learning called ‘trial-and-error’, and genetic e...
متن کاملSmall-footprint Keyword Spotting Using Deep Neural Network and Connectionist Temporal Classifier
Mainly for the sake of solving the lack of keyword-specific data, we propose one Keyword Spotting (KWS) system using Deep Neural Network (DNN) and Connectionist Temporal Classifier (CTC) on power-constrained small-footprint mobile devices, taking full advantage of general corpus from continuous speech recognition which is of great amount. DNN is to directly predict the posterior of phoneme unit...
متن کاملUsing Surface-Learning to improve Speech Recognition with Lipreading
We explore multimodal recognition by combining visual lipreading with acoustic speech recognition. We show that combining the visual and acoustic clues of speech improves the recog nition performance significantly especially in noisy environment. We achieve this with a hybrid speech recognition architecture, consisting of a new visual learning and tracking mechanism, a channel robust acoustic ...
متن کاملA Hybrid and bio-inspired Architecture approach for self-configuring behaviours in Cognitive Agents
In this work, an hybrid, self-configurable, multilayered and evolutionary subsumption architecture for cognitive agents is developed. Each layer of the multilayered architecture is modeled by one different Machine Learning System (MLS) based on bio-inspired techniques such as Extended Classifier Systems (XCS), Artificial Immune Systems (AIS), Neuro Connectionist Q-Learning (NQL) and Learning Cl...
متن کامل