Shulou(Shulou.com)06/03 Report--

This article mainly introduces the artificial neural network algorithm in the Internet, which has a certain reference value, interested friends can refer to, I hope you can learn a lot after reading this article, let the editor take you to know about it.

1. Adaptive resonance theory (ART) network

Adaptive Resonance Theory (ART) networks have different schemes. An ART-1 network consists of two layers, an input layer and an output layer. The two layers are fully interconnected, and the connection takes place in both positive (bottom-up) and feedback (top-down) directions.

When the ART-1 network is working, its training is continuous and includes the following algorithm steps:

The main results are as follows: (1) for all output neurons, if all warning weights of an output neuron are set to 1, it is called an independent neuron because it is not designated to represent any pattern type.

(2) A new input mode x is given.

(3) enable all output neurons to participate in stimulating competition.

(4) the winning output neuron is found from the competitive neuron, that is, the x ·W value of this neuron is the largest; at the beginning of training or when there is no better output neuron, the winning neuron may be an independent neuron.

(5) check whether the input mode x is similar enough to the vigilance vector V of the winning neuron.

(6) if r ≥ p, that is, there is resonance, turn to step (7); otherwise, the winning neuron is temporarily unable to compete further, and turn to step (4), and repeat this process until there are no more capable neurons.

2. Learning Vector quantization (LVQ) network

Learning vector quantization (LVQ) network is composed of three layers of neurons, namely, input conversion layer, hidden layer and output layer. The network is completely connected between the input layer and the hidden layer, while there is a partial connection between the hidden layer and the output layer, and each output neuron is connected with different groups of hidden neurons.

The simplest LVQ training steps are as follows:

(1) preset the initial weight of the reference vector.

(2) provide a training input mode for the network.

(3) calculate the Euclidean distance between the input mode and each reference vector.

(4) update the weight of the reference vector closest to the input mode (that is, the reference vector of the winning hidden neuron). If the winning implicit neuron belongs to the buffer connected to the output neuron in the same class as the input mode, then the reference vector should be closer to the input mode. Otherwise, the reference vector leaves the input mode.

(5) go to step (2) and repeat the process with a new training input mode until all training modes are correctly classified or a termination criterion is met.

3.Kohonen network

Kohonen network or self-organizing feature map network consists of two layers, one input buffer layer is used to receive input patterns, and the other is output layer. The neurons in output layer are generally arranged in a regular two-dimensional array, and each output neuron is connected to all input neurons. The connection weight forms a component of a reference vector connected to a known output neuron.

Training a Kohonen network involves the following steps:

(1) preset small random initial values for the reference vectors of all output neurons.

(2) provide a training input mode for the network.

(3) determine the winning output neuron, that is, the neuron whose reference vector is closest to the input mode. The Euclidean distance between the reference vector and the input vector is usually used as a distance measurement.

(4) update the reference vector of winning neuron and its nearest neighbor reference vector. These reference vectors are closer to the input vector. For the winning reference vector, the adjustment is the largest, while for the neurons farther away, the size of the neighborhood of the reduced adjusted neurons decreases relatively with the progress of the training. At the end of the training, only the reference vector of the winning neurons is adjusted.

4.Hopfield network

Hopfield network is a typical recursive network, which usually accepts only binary input (0 or 1) and bipolar input (+ 1 or-1). It contains a single layer of neurons, each of which is connected with all other neurons to form a recursive structure.

Thank you for reading this article carefully. I hope the article "what are the artificial neural network algorithms on the Internet" shared by the editor will be helpful to everyone? at the same time, I also hope that you will support and pay attention to the industry information channel. more related knowledge is waiting for you to learn!

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.