Deep learning is an advanced type of machine learning architecture employed by neural networks, most commonly by "convolutional neural networks." Deep learning is used in applications such as computer vision, self-driving cars, natural language processing and online advertising. For example, deep learning enables facial recognition to be more accurate, and it allows medical scans to be interpreted without human analysis.
In the training phase of a deep learning model, thousands of images of similar objects, such as a car, truck, horse or human being, are input as examples. The image is divided into pixels that are connected to several layers, each layer identifying a different block of pixels. By the time the image reaches the final layer, the input pattern has been identified. These are the so-called "hidden layers" between the input and output of a deep learning model. See convolutional neural network
The deep learning phase turns the neural network into the "inference engine," which does the actual processing such as identifying an object or making a decision. The greater number of layers in the training phase, the more accurate the inference engine and the better the results. See DLA
, machine learning
, neural network
Algorithms Make Mistakes
Deep Learning in the Hierarchy
Deep learning algorithms can be fooled. A famous example is mistaking a muffin for a puppy. Like a CAPTCHA, this verification test is used to ensure the viewer is human and not a bot, and images such as these can confuse an algorithm (see CAPTCHA
Deep learning is a subset within machine learning, which is a major category of artificial intelligence (AI).