Neural circuits for pattern recognition with small total wire length
نویسندگان
چکیده
One of the most basic pattern recognition problems is whether a certain local feature occurs in some linear array to the left of some other local feature. We construct in this article circuits that solve this problem with an asymptotically optimal number of threshold gates. Furthermore it is shown that much fewer threshold gates are needed if one employs in addition a small number of winner-take-all gates. In either case the circuits that are Research for this article was partially supported by the the Fonds zur Förderung der wissenschaftlichen Forschung (FWF), Austria, project P12153, and the NeuroCOLT project of the EC.
منابع مشابه
An Improved Standard Cell Placement Methodology using Hybrid Analytic and Heuristic Techniques
In recent years, size of VLSI circuits is dramatically grown and layout generation of current circuits has become a dominant task in design flow. Standard cell placement is an effective stage of physical design and quality of placement affects directly on the performance, power consumption and signal immunity of design. Placement can be performed analytically or heuristically. Analytical placer...
متن کاملAn Evaluation of Mahalanobis-Taguchi System and Neural Network for Multivariate Pattern Recognition
The Mahalanobis-Taguchi System is a diagnosis and predictive method for analyzing patterns in multivariate cases. The goal of this study is to compare the ability of the Mahalanobis- Taguchi System and a neural-network to discriminate using small data sets. We examine the discriminant ability as a function of data set size using an application area where reliable data is publicly available. The...
متن کاملWire length as a circuit complexity measure
We introduce wire length as a salient complexity measure for analyzing the circuit complexity of sensory processing in biological neural systems. This new complexity measure is applied in this paper to two basic computational problems that arise in translationand scale-invariant pattern recognition, and hence appear to be useful as benchmark problems for sensory processing. We present new circu...
متن کاملFoundations for a Circuit Complexity Theory of Sensory Processing
We introduce total wire length as salient complexity measure for an analysis of the circuit complexity of sensory processing in biological neural systems and neuromorphic engineering. Furthermore we introduce a set of basic computational problems that apparently need to be solved by circuits for translationand scale-invariant sensory processing. Finally we exhibit a number of circuit design str...
متن کاملPattern Recognition in Control Chart Using Neural Network based on a New Statistical Feature
Today for the expedition of the identification and timely correction of process deviations, it is necessary to use advanced techniques to minimize the costs of production of defective products. In this way control charts as one of the important tools for the statistical process control in combination with modern tools such as artificial neural networks have been used. The artificial neural netw...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Theor. Comput. Sci.
دوره 287 شماره
صفحات -
تاریخ انتشار 2001