Deep Learning

What is Deep Learning?

Deep Learning is a machine learning technique that constructs artificial neural networks to mimic the structure and function of the human brain. In practice, deep learning, also known as deep structured learning or hierarchical learning, uses a large number hidden layers -typically more than 6 but often much higher - of nonlinear processing to extract features from data and transform the data into different levels of abstraction (representations). 

As an example, assume the input data is a matrix of pixels. The first layer typically abstracts the pixels and recognizes the edges of features in the image. The next layer might build simple  features  from the edges such as leaves and branches. The next layer could then recognize a tree and so on. The data passing from one layer to the next is considered a transformation, turning the output of one layer into the input for the next. Each layer corresponds with a different level of abstraction and the machine can learn which features of the data to place in which layer/level on its own. Deep learning is differentiated from traditional “shallow learning” because it learns much deeper levels of hierarchical abstraction and representations.

Why is Deep Learning Important?

This learning technique is a groundbreaking tool for processing large quantities of data, since the performance of the machine improves as it analyzes more data.  As the amount of data increases, the machine becomes more adept at recognizing even hidden patterns among the data. Because the machine is also learning from the processed data, it is able to perform feature extraction and abstraction automatically from the raw data with little to no human input.

Practical Uses of Deep Learning

  • Automatic Speech Recognition – All major commercial speech recognition systems (think your smart phone assistant) use a deep learning technique with recurrent neural networks currently being the most popular.

  • Computer Vision – Images are used to train the machine to recognize features and now the machines are demonstrating “superhuman” accuracy for image recognition.
  • Natural Language Processing – Modern deep learning techniques have led to improvements in translation and language modeling. Google Translate uses deep learning techniques to translate based on the semantics of an entire sentence instead of just memorizing phrase-to-phrase translations.