Artificial Neural Networks


    In Context

    • Artificial Neural Networks are an important breakthrough in Artificial Intelligence & Deep Learning. 

    About Artificial Neural Networks

    • Neural networks are a set of algorithms, modeled loosely after the human brain, that are designed to recognize patterns.
    • An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain.
    • Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.
    • An artificial neuron receives a signal then processes it and can signal neurons connected to it. The “signal” at a connection is a real number, and the output of each neuron is computed by some non-linear function of the sum of its inputs.
      • The connections are called edges.
    • Back propagation: A feedback or difference between intended output and the input is computed at each layer and this difference is used to tune the parameters to each program. 
      • This method is called back propagation and it is an essential component to the Neural Network.

    Advantages of Artificial Neural Networks (ANN)

    • Neural networks help us cluster and classify: You can think of them as a clustering and classification layer on top of the data you store and manage.
    • Neural networks can also extract features that are fed to other algorithms for clustering and classification; so you can think of deep neural networks as components of larger machine-learning applications involving algorithms for reinforcement learning, classification and regression.
    • Storing information on the entire network: Information such as in traditional programming is stored on the entire network, not on a database. The disappearance of a few pieces of information in one place does not prevent the network from functioning.
    • Ability to work with incomplete knowledge:  After ANN training, the data may produce output even with incomplete information. The loss of performance here depends on the importance of the missing information.
    • Having fault tolerance:  Corruption of one or more cells of ANN does not prevent it from generating output. This feature makes the network fault tolerant.
    • Having a distributed memory: In order for ANN to be able to learn, it is necessary to determine the examples and to teach the network according to the desired output by showing these examples to the network.
      • The network’s success is directly proportional to the selected instances, and if the event cannot be shown to the network in all its aspects, the network can produce false output
    • Gradual corruption:  A network slows over time and undergoes relative degradation. The network problem does not immediately corrode.
    • Ability to make machine learning: Artificial neural networks learn events and make decisions by commenting on similar events.
    • Parallel processing capability:  Artificial neural networks have numerical strength that can perform more than one job at the same time.

    Disadvantages of Artificial Neural Networks (ANN)

    • Hardware dependence:  Artificial neural networks require processors with parallel processing power, in accordance with their structure. For this reason, the realization of the equipment is dependent.
    • Unexplained behavior of the network: This is the most important problem of ANN. When ANN produces a probing solution, it does not give a clue as to why and how. This reduces trust in the network.  
    • Determination of proper network structure:  There is no specific rule for determining the structure of artificial neural networks. Appropriate network structure is achieved through experience and trial and error.
    • Difficulty of showing the problem to the network:  ANNs can work with numerical information. Problems have to be translated into numerical values before being introduced to ANN. The display mechanism to be determined here will directly influence the performance of the network. This depends on the user’s ability.
    • The duration of the network is unknown: The network is reduced to a certain value of the error on the sample means that the training has been completed. This value does not give us optimum results.

    Source: TH