Meta-algorithm GENMODEL: Generalizing over three learning settings using observation tables
نویسنده
چکیده
We present a learning algorithm for regular languages that unifies three existing ones for the settings of minimally adequate teacher learning, learning from membership queries and positive data, and learning from positive and negative data, respectively. We choose these three algorithms as an example to back up the conjecture that the learning process of every algorithm for the class of regular languages founded on the retrieval of equivalence classes under the Myhill-Nerode relation can be mapped to an observation table as introduced by Angluin [1]. Different aspects of this generalization and suggestions for possible (architectural and theoretical) extensions are discussed in the second part of the paper.
منابع مشابه
Generalizing over Several Learning Settings
We recapitulate regular one-shot learning from membership and equivalence queries, positive and negative finite data. We present a meta-algorithm that generalizes over as many settings involving one or more of those information sources as possible and covers the whole range of combinations allowing inference with polynomial complexity. The algorithm uses the concept of an observation table as a...
متن کاملDifferential Equations ( Qualitative Differential Equations ) Qualitative Constraints Qualitative Simulation
ion Perturbation Statistical Analysis (e.g. Regression Methods) Dynamic System System Behavior Quantitative System Behavior Qualitative System Behavior (Qualitative States) (Numerical Data) Inductive Learning (e.g. GENMODEL) Figure 1. Qualitative reasoning is an abstraction of mathematical reasoning with di erential equations and continuously di erentiable functions. and an initial state, we ca...
متن کاملSIZE AND GEOMETRY OPTIMIZATION OF TRUSSES USING TEACHING-LEARNING-BASED OPTIMIZATION
A novel optimization algorithm named teaching-learning-based optimization (TLBO) algorithm and its implementation procedure were presented in this paper. TLBO is a meta-heuristic method, which simulates the phenomenon in classes. TLBO has two phases: teacher phase and learner phase. Students learn from teachers in teacher phases and obtain knowledge by mutual learning in learner phase. The suit...
متن کاملCombining heterogeneous classifiers for relational databases
Most enterprise data is distributed in multiple relational databases with expert-designed schema. Using traditional single-table machine learning techniques over such data not only incur a computational penalty for converting to a flat form (mega-join), even the human-specified semantic information present in the relations is lost. In this paper, we present a practical, twophase hierarchical me...
متن کاملComposing Meta-Policies for Autonomous Driving Using Hierarchical Deep Reinforcement Learning
Rather than learning new control policies for each new task, it is possible, when tasks share some structure, to compose a "meta-policy" from previously learned policies. This paper reports results from experiments using Deep Reinforcement Learning on a continuous-state, discrete-action autonomous driving simulator. We explore how Deep Neural Networks can represent meta-policies that switch amo...
متن کامل