Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 40 for “"Computational learning theory"”.
-
Topics in computational learning theory and graph algorithms
"The distribution-independent model of concept learning from examples (""PAC-learning"") due to Valiant is investigated. It has previously been shown that the existence of an Occam algorithm for a class of concepts is a sufficient condition for the PAC-learnability of that class. (An Occam …
-
Uncertainty management in the activated sludge process: Innovative applications of computational learning theory.
… model identification procedure is viewed as a learning problem or, equivalently, an information transfer from a set of real data into the process model. An innovative mathematical framework for the identification and validation of dynamic mechanistically based WWT process models is developed. …
-
Matters Horn and other features in the computational learning theory landscape: The notion of membership
Current knowledge representation research has sought to provide schemes for encoding knowledge about how a given system behaves, with the goal being accuracy and utility. Ideally, the goal of encoding knowledge is not the task of encoding, but the product of the encoding task. If such encodings are …
-
Geometric Concept Learning and Related Topics
… serves as an illustration of some of the useful learning paradigms that are discovered by research in computational learning theory.
-
Learning Pattern Languages from a Small Number of Helpfully Chosen Examples
… introduced by Angluin in 1980. Since that time, learning of pattern languages has been a topic of great interest in the research area of computational learning theory, mainly because of its relevance for many applications. Areas in which patterns are suitable for modelling data are for example …
-
Lower bounds in communication complexity and learning theory via analytic methods
… in the contexts of communication complexity and computational learning theory. In the former case, one seeks to understand which distributed computations require a significant amount of communication among the parties involved. In the latter case, one aims to rigorously explain why computers …
-
Algorithm for Learning from a Random Walk Oracle
Learning Disjunctive Normal Form and Threshold of Parity functions are well-studied problems in computational learning theory. Under different learning models we can achieve different time complexities with respect to the size of the input. In this thesis, I consider using an oracle whose power …
-
A Proposed Algorithm Toward Uniform-distribution Monotone DNF Learning
… model of Probably Approximately Correct (PAC) learning from random examples and brought up the problem of whether polynomial-size DNF functions are PAC learnable in polynomial time. It has been about twenty years that the DNF learning problem has been widely regarded as one of the most …
-
Definable families of finite Vapnik Chervonenkis dimension
… notion with applications in machine learning, stability theory, and statistics. We explore what effect model theoretic structure has on the VC dimension of formulas, considered as parameterized families of sets, with respect to long disjunctions and conjunctions. If the growth in VC …
-
Learning bisimulation
Computational learning theory is a branch of theoretical computer science that re-imagines the role of an algorithm from an agent of computation to an agent of learning. The operations of computers become those of the human mind; an important step towards illuminating the limitations of artificial …
-
Adaptive learning and cryptography
Significant links exist between cryptography and computational learning theory. Cryptographic functions are the usual method of demonstrating significant intractability results in computational learning theory as they can demonstrate that certain problems are hard in a representation independent …
-
Learning hypertrees with shortest path queries
One branch of computational learning theory focuses on algorithms for learning discrete structured objects from queries. In this context, we consider the problem of learning a labeled hypergraph from a given family of hypergraphs using shortest path (SP) queries. An SP query specifies two vertices …
-
Practical Improvements in Applied Spectral Learning
Spectral learning algorithms, which learn an unknown function by learning a spectral representation of the function, have been widely used in computational learning theory to prove many interesting learnability results. These algorithms have also been successfully used in real-world applications. …
-
Learning algorithms for restricted neural networks.
The problem of supervised learning can be phrased in terms of finding a good approximation to some unknown target function f, based on observing f's values on some examples drawn randomly according to some underlying distribution. Unfortunately, finding an algorithm that efficiently learns simple …
-
Generalization of boosting algorithms and applications of Bayesian inference for massive datasets
In recent years statisticians, computational learning theorists, and engineers have developed more advance techniques to learn complex non-linear relationships from datasets. However, not only have models increased in complexity, but also datasets have outgrown many of the computational methods for …
-
Sample complexity of robust learning against evasion attacks
… to understand the vulnerability of machine learning models to adversarial attacks. One of the fundamental problems in adversarial machine learning is to quantify how much training data is needed in the presence of so-called evasion attacks, where data is corrupted at test time. In this …
-
New computational and statistical characterizations of neural network learning
A foundational goal of machine learning theory is to characterize the inherent computational and statistical complexity of some of the most basic tasks in machine learning. In this thesis, we present new results concerning two such tasks in neural network learning and beyond. First, we study the …
-
On the theory of Lipschitz continuous machine learning
<p>The field of machine learning theory plays an essential role in establishing the mathematical foundations and performance boundaries of data-driven modelling techniques. By providing a rigorous analysis of the underlying properties of an algorithm, theoretical machine learning guides the …
-
On Concept Classes With Low No-Clash Teaching Dimension
Computational Learning Theory studies the complexity of learning for various formal models of machine learning. Such models use a learning algorithm A fed with a set of labelled data for a target concept belonging to a given class of concepts, and A produces a mapping that is used to accurately …
-
Partial identifiability and misspecification in inverse reinforcement learning
<p>The aim of Inverse Reinforcement Learning (IRL) is to infer a reward function <em>R</em> from a policy π. This problem is difficult, for several reasons. First of all, there are typically multiple reward functions which are compatible with a given policy; this means that the reward function is …
Page 1 of 2