Search for "Neural networks" in article titles:

1. Neural networks: Neural networks are computer models that attempt to imitate the parallel processing that occurs in the human brain. They are typically viewed as having some number of nodes, each with one or more inputs and one output. [100%] 2023-03-17 [Technology]
2. Recurrent Neural Networks: A recurrent neural network (RNN) is a class of artificial neural networks where connections between nodes form a directed graph along a temporal sequence. This allows it to exhibit temporal dynamic behavior. [81%] 2023-12-21 [Neural Networks]
3. Dilution (neural networks): Dilution and dropout (also called DropConnect) are regularization techniques for reducing overfitting in artificial neural networks by preventing complex co-adaptations on training data. They are an efficient way of performing model averaging with neural networks. (Neural networks) [81%] 2023-11-24 [Artificial neural networks] [Deep learning]...
4. Recurrent neural networks: A recurrent neural network (RNN) is any network whose neurons send feedback signals to each other. This concept includes a huge number of possibilities. [81%] 2021-12-24 [Computational Intelligence] [Recurrent Neural Networks]...
5. Artificial Neural Networks: In many cases technology adopts solutions that were generated by evolutionary processes in biology. The same can be applied on Artificial Neural Networks (ANN). [81%] 2023-12-21 [Machine learning]
6. Dropout (neural networks): Dropout is a regularization technique patented by Google for reducing overfitting in neural networks by preventing complex co-adaptations on training data. It is a very efficient way of performing model averaging with neural networks. (Neural networks) [81%] 2023-12-21 [Artificial neural networks]
7. Rectifier (neural networks): In the context of artificial neural networks, the rectifier or ReLU (rectified linear unit) activation function is an activation function defined as the positive part of its argument: where x is the input to a neuron. This is also known ... (Neural networks) [81%] 2023-12-31 [Artificial neural networks]
8. Rectifier (neural networks): In the context of artificial neural networks, the rectifier or ReLU (rectified linear unit) activation function is an activation function defined as the positive part of its argument: where x {\displaystyle x} is the input to a neuron. This is ... (Neural networks) [81%] 2024-06-11 [Artificial neural networks]
9. Confabulation (neural networks): A confabulation, also known as a false, degraded, or corrupted memory, is a stable pattern of activation in an artificial neural network or neural assembly that does not correspond to any previously learned patterns. The same term is also applied ... (Neural networks) [81%] 2024-09-02 [Artificial neural networks] [Neural circuits]...
10. Instantaneously trained neural networks: Instantaneously trained neural networks are feedforward artificial neural networks that create a new hidden neuron node for each novel training sample. The weights to this hidden neuron separate out not only this training sample but others that are near it ... [70%] 2023-12-21 [Learning] [Artificial neural networks]...
11. Bidirectional recurrent neural networks: Bidirectional recurrent neural networks (BRNN) connect two hidden layers of opposite directions to the same output. With this form of generative deep learning, the output layer can get information from past (backwards) and future (forward) states simultaneously. (Type of artificial neural network) [70%] 2023-12-26
12. Physics-informed neural networks: Physics-informed neural networks (PINNs) are a type of universal function approximators that can embed the knowledge of any physical laws that govern a given data-set in the learning process, and can be described by partial differential equations (PDEs ... (Physics) [70%] 2023-12-22 [Differential equations] [Deep learning]...
13. Learning and neural networks: A Perceptron is a type of Feedforward neural network which is commonly used in Artificial Intelligence for a wide range of classification and prediction problems. Here, however, we will look only at how to use them to solve classification problems. [70%] 2024-01-12 [Artificial intelligence] [Social psychology]...
14. Types of artificial neural networks: There are many types of artificial neural networks (ANN). Artificial neural networks are computational models inspired by biological neural networks, and are used to approximate functions that are generally unknown. (Classification of Artificial Neural Networks (ANNs)) [63%] 2023-12-21 [Neural network architectures] [Computational statistics]...
15. Types of artificial neural networks: There are many types of artificial neural networks (ANN). Artificial neural networks are computational models inspired by biological neural networks, and are used to approximate functions that are generally unknown. (Classification of Artificial Neural Networks (ANNs)) [63%] 2023-10-31 [Computational statistics] [Artificial neural networks]...
16. History of artificial neural networks: The simplest kind of feedforward neural network is a linear network, which consists of a single layer of output nodes; the inputs are fed directly to the outputs via a series of weights. The sum of the products of the ... (Aspect of history) [63%] 2023-12-21 [Computational statistics] [Artificial neural networks]...
17. Mathematics of artificial neural networks: An artificial neural network (ANN) combines biological principles with advanced statistics to solve problems in domains such as pattern recognition and game-play. ANNs adopt the basic model of neuron analogues connected to each other in a variety of ways. [63%] 2023-12-26 [Computational statistics] [Artificial neural networks]...
18. Mathematical modeling of neural networks: Welcome to the Wikiversity learning project for Mathematical modeling of neural networks. This "learn by doing" project provides information about how to work with mathematical models of neural networks and space for discussion of neural network models. [63%] 2023-12-21 [Neurobiology] [Resources last modified in May 2019]...
19. History of artificial neural networks: The simplest kind of feedforward neural network is a linear network, which consists of a single layer of output nodes; the inputs are fed directly to the outputs via a series of weights. The sum of the products of the ... (Aspect of history) [63%] 2023-12-22 [Computational statistics] [Artificial neural networks]...
20. Large width limits of neural networks: File:Infinitely wide neural network.webm Artificial neural networks are a class of models used in machine learning, and inspired by biological neural networks. They are the core component of modern deep learning algorithms. [57%] 2023-12-21 [Deep learning] [Artificial neural networks]...