You are on page 1of 2

Deep learning 

Deep learning is a subset of machine learning in artificial intelligence (AI) that has
networks capable of learning unsupervised from data that is unstructured or unlabeled.
Also known as deep neural learning or deep neural network.

Deep learning networks can be successfully applied to big data for knowledge discovery,
knowledge application, and knowledge-based prediction. In other words, deep
learning can be a powerful engine for producing actionable results.

To recap the differences between the two: Machine learning uses algorithms to parse


data, learn from that data, and make informed decisions based on what it has
learned. Deep learning structures algorithms in layers to create an "artificial neural
network” that can learn and make intelligent decisions on its own.

The “deep” in Deep Learning refers to the circumstance that we derive the output for our
input by passing it through multiple layers / a hierarchy of transformations (i.e., we go
through some depth of transforms), instead of having a single, linear formula that tells us
the output value directly.

Earlier versions of neural networks such as the first perceptrons were shallow, composed
of one input and one output layer, and at most one hidden layer in between. More than
three layers (including input and output) qualifies as “deep” learning.

Deep learning is a machine learning technique that teaches computers to do


what comes naturally to humans: learn by example. ... In deep learning, a
computer model learns to perform classification tasks directly from images, text, or
sound.

Why is Deep Learning Important? The ability to process large numbers of features
makes deep learning very powerful when dealing with unstructured data. However, deep
learning algorithms can be overkill for less complex problems because they require access
to a vast amount of data to be effective.

Deep learning then can be defined as neural networks with a large number
of parameters and layers in one of four fundamental network
architectures:
 Unsupervised Pre-trained Networks.
 Convolutional Neural Networks.
 Recurrent Neural Networks.
 Recursive Neural Networks.

You might also like