what is  neural networks

neural networks

artificial neural networks

Artificial neural networks (ANNs) or connectionist systems are computing systems inspired by the biological neural networks that constitute animal brains. Such systems learn to perform tasks by considering examples (progressively improving their capability), usually without task-specific programming. For example, in image recognition, they use those images by analyzing example images labeled as "cat" or "no cat" by analyzing example images and using analytical results to identify cats in other images. can learn to identify which includes cats. They have found most use in applications difficult to express with traditional computer algorithms using rule-based programming.

An ANN is based on a collection of connected units called artificial neurons, (analogous to biological neurons in the biological brain). Each connection (synapse) between neurons can transmit a signal to another neuron. The receiving (postsynaptic) neuron can process the signal and then signal to the downstream neurons connected to it. Neurons can have states, usually represented by real numbers, typically between 0 and 1. Neurons and synapses can also have a weight that varies as learning proceeds, which can increase or decrease the strength of the signal it sends downstream.

Typically, neurons are organized in layers. Different layers can perform different types of transformations on their inputs. Signals travel from the first (input) to the last (output) layer, possibly after passing the layers several times.

The original goal of the neural network approach was to solve problems in the same way that the human brain does. Over time, the focus shifted to matching specific mental abilities, leading to deviations from biology such as backpropagation, or passing information in the reverse direction and adjusting networks to reflect that information.

Neural networks have been used on a variety of tasks including computer vision, speech recognition, machine translation, social network filtering, playing boards and video games, and medical diagnosis.

As of 2017, neural networks typically contain a few thousand to a few million units and millions of connections. Despite this number being several orders of magnitude less than the number of neurons on the human brain, these networks can perform many tasks at a level beyond humans (for example, recognizing faces.

deep neural network

Deep Neural Network (DNN) is an artificial neural network (ANN) consisting of several layers between the input and output layers. There are different types of neural networks but they always contain the same components: neurons, synapses, weights, biases, and functions. These components function similarly to the human brain and can be trained like any other ML algorithm. [citation needed]

For example, a DNN that is trained to recognize dog breeds will visit a given image and calculate the probability that the dog in the image is a certain breed. The user can review the results and choose which probabilities the network should display (above a certain threshold, etc.) and return the proposed label. Each mathematical manipulation is considered a layer, and complex DNNs consist of many layers, hence the name "deep" network.

DNNs can model complex non-linear relationships. DNN architectures generate compositional models where objects are expressed as a layered structure of primitives. [112] Additional layers enable the composition of features from lower layers, potentially modeling complex data with fewer units than shallow networks performing similarly. For example, it was proved that sparse multivariate polynomials are increasingly easier to approximate with DNNs than with shallow networks.

Deep architecture includes several variations of some of the basic approaches. Each architecture has found success in a specific domain. It is not always possible to compare the performance of multiple architectures, unless they have been evaluated on the same data set.

DNNs are generally feedforward networks in which data flows from the input layer to the output layer without looping. First, the DNN builds a map of virtual neurons and assigns random numerical values, or "weights," to the connections between them. The weights and the input are multiplied and return an output between 0 and 1. If the network does not accurately detect a particular pattern, an algorithm will adjust the weights. In this way the algorithm can make certain parameters more efficient, until it determines the correct mathematical manipulation to process the data as a whole.

Recurrent neural networks (RNNs), in which data can flow in any direction, are used for applications such as language modeling. Long-term memory is particularly effective for this experiment.

Convolutional deep neural networks (CNNs) are used in computer vision.  Automatic