Instantaneously Trained Neural Networks
نویسنده
چکیده
This paper presents a review of instantaneously trained neural networks (ITNNs). These networks trade learning time for size and, in the basic model, a new hidden node is created for each training sample. Various versions of the cornerclassification family of ITNNs, which have found applications in artificial intelligence (AI), are described. Implementation issues are also considered.
منابع مشابه
A Class of Instantaneously Trained Neural Networks
This paper presents FC networks that are instantaneously trained neural networks that allow rapid learning of non-binary data. These networks, which generalize the earlier CC networks, have been compared against Backpropagation (BP) and Radial Basis Function (RBF) networks and are seen to have excellent performance for prediction of time-series and pattern recognition. The networks can generali...
متن کاملAn FPGA implementation of Kak's instantaneously-trained, Fast-Classification neural networks
Motivated by a biologically plausible short-memory sketchpad, Kak's Fast Classification (FC) neural networks are instantaneously trained by using a prescriptive training scheme. Both weights and the topology for an FC network are specified with only two presentations of the training samples. Compared with iterative learning algorithms such as Backpropagation (which may require many thousands of...
متن کاملNeural Networks with Complex and Quaternion Inputs
Many neural network architectures operate only on real data and simple complex inputs. But there are applications where considerations of complex and quaternion inputs are quite desirable. Prior complex neural network models have generalized the Hopfield model, backpropagation and the perceptron learning rule to handle complex inputs. The Hopfield model for inputs and outputs falling on the uni...
متن کامل{ Real . Time Monitoring of Awj Nozzle Wear Using Artificial Neural Network
\nG ABSTRACT An abrasive waterjet nozzle wear monitoring and compensating mechanism using the frequency domain.acoustic signals geneiated by the jet exiting the nozzle, as input, is prbposed. An artificial neural network which forms the critical iart of this system is developed using the _back-propagatlon algorithm. The trained network is capable of determining the nozzle diameter corresponding...
متن کاملOn the use of back propagation and radial basis function neural networks in surface roughness prediction
Various artificial neural networks types are examined and compared for the prediction of surface roughness in manufacturing technology. The aim of the study is to evaluate different kinds of neural networks and observe their performance and applicability on the same problem. More specifically, feed-forward artificial neural networks are trained with three different back propagation algorithms, ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/cs/0601129 شماره
صفحات -
تاریخ انتشار 2006