Unsupervised Models C2.1 Feedforward models
نویسنده
چکیده
Feedforward unsupervised models cover a wide range of neural networks with various applications. In this section, we discuss three widely used models. (i) Kohonen’s selforganizing map, also called the Kohonen network , the self-organizing feature map, or the topological map, is intended to map a high-dimensional space into a oneor twodimensional space, preserving the topology of the input space; it has a strong biological plausibility and is basically intended to be used in applications where preserving the topology between input and output spaces is important (e.g. control, inverse mapping, image compression). It is an unsupervised model, but can be extended to a supervised one by adding a supplementary layer. In addition to the topology-conserving property, the Kohonen model also acts as a vector quantizer. (ii) The neural gas is another vector quantization algorithm that may be considered as a neural network method because it relies on the same principle of adaptation, may be represented in the form of a feedforward graph, and may be described by the same formalism as used in many other neural models. It is different from the Kohonen map in the sense that it does not have the topology preserving property but it generally performs better giving a smaller final distortion error. (iii) The neocognitron is a complex feedforward model formed by several layers each containing a large number of neurons. Its goal is to automatically detect features in two-dimensional arrays of points through self-organization and reinforcement principles. The network is built to be insensitive to shifts in position of the patterns or of small parts of them, thus also allowing for distorted patterns. The network is primarily intended to be used in feature extraction and pattern recognition tasks, for example in OCR (optical character recognition). C2.1.1 Kohonen’s self-organizing map C2.1.1.
منابع مشابه
Evaluation of Iranian electronic products manufacturing industries using an unsupervised model, ARAS, SAW, and DEA models
متن کامل
Attractor Dynamics in Feedforward Neural Networks
We study the probabilistic generative models parameterized by feedforward neural networks. An attractor dynamics for probabilistic inference in these models is derived from a mean field approximation for large, layered sigmoidal networks. Fixed points of the dynamics correspond to solutions of the mean field equations, which relate the statistics of each unit to those of its Markov blanket. We ...
متن کاملUsing Non-oscillatory Dynamics to Disambiguate Pattern Mixtures
This chapter describes a model which takes advantage of the time domain through feedback iterations that improve recognition and help disambiguate pattern mixtures. This model belongs to a class of models called generative models. It is based on the hypothesis that recognition centers of the brain reconstruct an internal copy of inputs using knowledge the brain has previously accumulated. Subse...
متن کاملOptimization of sediment rating curve coefficients using evolutionary algorithms and unsupervised artificial neural network
Sediment rating curve (SRC) is a conventional and a common regression model in estimating suspended sediment load (SSL) of flow discharge. However, in most cases the data log-transformation in SRC models causing a bias which underestimates SSL prediction. In this study, using the daily stream flow and suspended sediment load data from Shalman hydrometric station on Shalmanroud River, Guilan Pro...
متن کاملبررسی کارایی روشهای مختلف هوش مصنوعی و روش آماری در برآورد میزان رواناب (مطالعه موردی: حوزه شهید نوری کاخک گناباد)
Rainfall-runoff models are used in the field of hydrology and runoff estimation for many years, but despite existing numerous models, the regular release of new models shows that there is still not a model that can provide sophisticated estimations with high accuracy and performance. In order to achieve the best results, modeling and identification of factors affecting the output of the model i...
متن کامل