Blog: Deep Learning & Neural Network
Deep Learning is a part of Machine Learning which is based on Neural Networks(NN). The term, ‘deep’ in “Deep Learning” refers to the many layers through which the data is transformed. Each layer learns to transform input data into slightly more abstract and composite representation of data.
Deep Learning uses multiple layers of stacks of neurons to extract meaningful data from the provided raw input. For example, in image processing lower layers might be used to identify the curves and edges while the higher layers may identify whether the image contains human face or digits or alphabets. This learning from the data can be supervised, unsupervised or semi-supervised. Deep Learning has accelerated the growth of very smart machines exceeding to super human levels. It has been applied to fields like computer vision, speech recognition, natural language processing, etc.
A neural network is a Machine Learning algorithm which models complex data patterns in datasets. Neural networks are patterned after the operations of neurons in animal brain. It simply consists of neurons which operate in parallel and arranged in layers.
The first layer receives the information(raw input) and the successive layers receiving information from the preceding layers until the last layer which produces the output. Each neuron are highly interconnected to other neurons from other layers, like if a neuron is in layer n then it will be connected to many nodes in layer n-1(it’s input) and with layer n+1(it’s output).