Introduction to Neural Networks | HackThatCORE

Image Source: Becoming Human

Neural Network is like you can say it is the most hot topic in the field of Computer Science and also in Artificial Intelligence and its applications to make intelligent machines having qualities like Humans. To understand the Neural networks, we have to first make a clear understanding about how human brain works actually. Moreover we can say that an Artificial Neural Network (ANN) is an information processing model or paradig that is almost inspired by the biological Nervous or Human Nervous systems, like as i told you previously the human brain's information processing mechanism.
As we all know, the human brain is highly complex. Its working involves millions of layers of computing or we can say that it is a non-linear, complex and parallel computer. In terms of the speed of the brain, it can amaze us with its unbelievable performance. To recognize a face of a person our brain takes approximately 100-200 ms, where a conventional computer may take days.
Similarly, we can also consider the SONAR of a bat. By using this, bat's nervous system can detect the position of its prey even at the long distance. In addition to providing the information about how far away the prey is it conveys information about relative velocity of the target, size of target, the size of various features of target. How does a biological brain do this?


Our biological neuron consists of several parts. Let's introduce them one by one. Dendrite - It receives signals from other neurons. Soma (cell body) - It sums all the incoming signals to generate input. Axon - When the sum reaches a threshold value, neuron fires and the signal travels down the axon to the other neurons. Synapses - The pointof interconnections of one neuron with other neurons. The amount of signal transmitted depend upon the strength (synaptic weights) of the connections. The connections can be inhibitory (decreasing strength) or excitatory (increasing strength) in nature.
So, neural network, in general, is a highly interconnected network of billions of neurons with trillions of interconnections between them.
When a neuron receives excitatory input that is sufficiently large compared with its inhibitory input, it sends a spike of electrical activity down its axon. Learning occurs by changing the effectiveness of the synapses so that the influence of one neuron on another changes. We conduct these neural networks by first trying to deduce the essential features of neurons and their interconnections. We then typically program a computer to simukate these features.
So that's all for the basic introduction of a Neural Network. Further concepts will be available in future posts. Thank You