What Is Deep Learning

Deep Learning (also known as deep structured learning or Hierarchical learning) is a subdivision of machine learning in Artificial Intelligence that has networks which are capable of learning data representations, as opposed to task-specific algorithms. Learning can be supervised, semi-supervised or unsupervised. It deals with algorithms inspired by the structure and function of the brain, allowing computers to solve a host of complex problems that couldn't otherwise be tackled.

Deep Learning is being widely used in industries to solve large number of problems like.

Image Recognition: Deep Neural Nets are used to identify objects in an image. 

Voice Generation: Products like Amazon Alexa uses deep learning to generate voice and interact with humans.

Self Driving Vehicles: Google’s self driving car is based on Machine Learning and Deep Learning algorithms. It can drive at a precision of 98% in dark, while its raining and in high terrain areas.

Producing Music: Deep Learning can be used to produce music by feeding in music patterns and letting it analyze on its own. It can also be used to restore audio voices in silent movies.

Difference between Deep Learning , Machine Learning and Artificial Intelligence?

Deep learning is a specialized form of machine learning. A machine learning workflow starts with relevant features being manually extracted from images. The features are then used to create a model that categorizes the objects in the image. With a deep learning workflow, relevant features are automatically extracted from images. In addition, deep learning performs “end-to-end learning” – where a network is given raw data and a task to perform, such as classification, and it learns how to do this automatically.

Another key difference is deep learning algorithms scale with data, whereas shallow learning converges. Shallow learning refers to machine learning methods that plateau at a certain level of performance when you add more examples and training data to the network.

A key advantage of deep learning networks is that they often continue to improve as the size of your data increases.

Deep learning is applied in many areas of artificial intelligence such as speech recognition, image recognition, natural language processing, robot navigation systems, self-driving cars etc. 

Below mentioned are some applications of deep learning:

· Colorization of Black and White Images.

· Adding Sounds To Silent Movies.

· Automatic Machine Translation.

· Object Classification in Photographs.

· Automatic Handwriting Generation.

· Character Text Generation.

· Image Caption Generation.

· Automatic Game Playing.

. Behavioural analysis 

Deep Learning in Future:

Unsupervised Feature Learning seems to be a future trend. Since both neural network and data sets would grow bigger and bigger, labeling everything we observed would become unreasonable and unrealistic. Unsupervised feature learning approaches, like Auto encoders, would automatically make conclusions from similar observations. Then manually labeling these conclusions can be practical, and this is the way curiosity of computers are satisfied.

Deep Reinforcement Learning is another future direction. Due to the success of human-level control of playing atari games, RL based learning are growing more and more popular. And the model works more like to a human brain, it interacts with the noisy environment and make precise decisions upon given scalar reward value.