Applying Divide and Conquer to Large Scale Pattern Recognition Tasks
نویسندگان
چکیده
Rather than presenting a speciic trick, this paper aims at providing a methodology for large scale, real-world classiication tasks involving thousands of classes and millions of training patterns. Such problems arise in speech recognition, handwriting recognition and speaker or writer identiication, just to name a few. Given the typically very large number of classes to be distinguished, many approaches focus on para-metric methods to independently estimate class conditional likelihoods. In contrast, we demonstrate how the principles of modularity and hierarchy can be applied to directly estimate posterior class probabilities in a connectionist framework. Apart from ooering better discrimination capability, we argue that a hierarchical classiication scheme is crucial in tackling the above mentioned problems. Furthermore, we discuss training issues that have to be addressed when an almost innnite amount of training data is available.
منابع مشابه
Free Vibration Analysis of Repetitive Structures using Decomposition, and Divide-Conquer Methods
This paper consists of three sections. In the first section an efficient method is used for decomposition of the canonical matrices associated with repetitive structures. to this end, cylindrical coordinate system, as well as a special numbering scheme were employed. In the second section, divide and conquer method have been used for eigensolution of these structures, where the matrices are in ...
متن کاملCode Breaking for Automatic Speech Recognition
Code Breaking is a divide and conquer approach for sequential pattern recognition tasks where we identify weaknesses of an existing system and then use specialized decoders to strengthen the overall system. We study the technique in the context of Automatic Speech Recogniton. Using the lattice cutting algorithm, we first analyze lattices generated by a state-of-the-art speech recognizer to spot...
متن کاملDivide-and-Conquer Parallelism for Learning Mixture Models
From the viewpoint of load balancing among processors, the acceleration of machine-learning algorithms by using parallel loops is not realistic for some models involving hierarchical parameter estimation. There are also other serious issues such as memory access speed and race conditions. Some approaches to the race condition problem, such as mutual exclusion and atomic operations, degrade the ...
متن کاملDivide and Conquer Networks
We consider the learning of algorithmic tasks by mere observation of input-output pairs. Rather than studying this as a black-box discrete regression problem with no assumption whatsoever on the input-output mapping, we concentrate on tasks that are amenable to the principle of divide and conquer, and study what are its implications in terms of learning. This principle creates a powerful induct...
متن کامل