What is deep learning?

What is deep learning?

Deep learning is a subset of machine learning that involves the use of neural networks with three or more layers to simulate the human brain's behavior [0]. Deep learning is a modern variation of machine learning that is concerned with an unbounded number of layers of bounded size, which permits practical application and optimized implementation, while retaining theoretical universality under mild conditions. The word "deep" in deep learning refers to the use of multiple layers in the network [1]. Deep learning is a machine learning technique that teaches computers to learn by example [2].

Deep learning models can achieve state-of-the-art accuracy, sometimes exceeding human-level performance. Models are trained by using a large set of labeled data and neural network architectures that contain many layers. Deep learning is a key technology behind driverless cars, enabling them to recognize a stop sign, or to distinguish a pedestrian from a lamppost. It is also the key to voice control in consumer devices like phones, tablets, TVs, and hands-free speakers [2].

Deep learning helps to disentangle abstractions and pick out which features improve performance. For supervised learning tasks, deep learning methods eliminate feature engineering by translating the data into compact intermediate representations akin to principal components and derive layered structures that remove redundancy in representation. Deep learning algorithms can be applied to unsupervised learning tasks. This is an important benefit because unlabeled data is more abundant than labeled data. Examples of deep structures that can be trained in an unsupervised manner are deep belief networks [1].

Deep learning architectures, such as deep neural networks, deep belief networks, deep reinforcement learning, recurrent neural networks, convolutional neural networks, and transformers, have been applied to fields including computer vision, speech recognition, natural language processing, machine translation, bioinformatics, drug design, medical image analysis, climate science, material inspection, and board game programs, where they have produced results comparable to and in some cases surpassing human expert performance [1].

Deep learning is being successfully applied to financial fraud detection, tax evasion detection, and anti-money laundering [1]. Deep learning is also used in industries from automated driving to medical devices. For example, automotive researchers are using deep learning to automatically detect objects such as stop signs and traffic lights. In addition, deep learning is used to detect pedestrians, which helps decrease accidents. Cancer researchers are using deep learning to automatically detect cancer cells. Teams at UCLA built an advanced microscope that yields a high-dimensional data set used to train a deep learning application to accurately identify cancer cells [2].

Deep learning requires large amounts of labeled data and substantial computing power. High-performance GPUs have a parallel architecture that is efficient for deep learning. When combined with clusters or cloud computing, this enables development teams to reduce training time for a deep learning network from weeks to hours or less [2].

In summary, deep learning is a subset of machine learning that involves the use of neural networks with multiple layers to simulate the human brain's behavior. It achieves state-of-the-art accuracy in various fields and is being used in industries from automated driving to medical devices. Deep learning requires large amounts of labeled data and substantial computing power.