What Is ‘Deep Learning’?
Deep learning is a machine learning technique that trains, computers to do what comes naturally to humans: learn by example. Deep learning is a key technology behind driverless automated cars, enabling them to recognize sign boards, or to distinguish a pedestrian crossing the road. It is the key to voice control in consumer devices like phones, tablets and TVs. In deep learning, a computer model learns to perform classification tasks directly from images or text or sound.
Deep learning requires large amounts of labeled data. For example, driverless car development requires millions of images and thousands of hours of video. It requires substantial computing power. High-performance GPUs(Graphics Processing Unit) have a parallel architecture that is efficient for deep learning. When combined with clusters or cloud computing, it reduces training time for a deep learning network from weeks to hours or less.
How Deep Learning Works?
Most deep learning methods use neural network architectures, which is why deep learning models are referred to as deep neural networks. The term usually refers to the number of hidden layers in the neural network. Traditional neural networks contain 2-3 hidden layers, while deep networks can have as many as 150. Deep learning models are trained by using large sets of labeled data and neural network architectures that learn features directly from the labeled data. MATLAB makes deep learning easy. With tools and functions for managing large data sets, MATLAB also offers specialized toolboxes for working with machine learning and neural networks.
Examples of Deep Learning at Work:
Automated Driving: Automotive researchers are using deep learning to automatically detect objects such as sign boards and traffic lights. In addition, deep learning is used to detect pedestrians crossing the road, which helps decrease accidents.
Medical Research: Cancer researchers are using deep learning to detect cancer cells. An advanced microscope was built that yields a high-dimensional data set used to train a deep learning application to accurately identify cancer cells.
Aerospace and Defense: Deep learning is used to identify and locate areas of interests from satellites, and identify safe or unsafe zones for hiding for military troops.
Industrial Automation: Deep learning is helping to improve safety of workers around heavy machinery by automatically detecting when people or objects are within an unsafe distance of machines.
