Applications of deep learning

Machine learning in general, and deep learning in particular, are producing more and more astonishing results in terms of the quality of predictions, feature detection, and classification. Many of these recent results have made the news. Such is the pace of progress, that some experts are worrying that machines will soon be more intelligent than humans. But I hope that any such fears you might have will be alleviated after you have read this book. For better or worse, we're still far from human-level intelligence. 

In Chapter 2, Neural Networks, we mentioned how deep learning algorithms have occupied the leaderboard of the ImageNet competition. They are successful enough to make the jump from academia to industry. Let's now talk about some real-world use cases of deep learning:

• Nowadays, new cars have a suite of safety and convenience features that aim to make the driving experience safer and less stressful. One such feature is automated emergency braking if the car sees an obstacle. Another one is lane-keeping assist, which allows the vehicle to stay in its current lane without the driver needing to make corrections with the steering wheel. To recognize lane markings, other vehicles, pedestrians, and cyclists, these systems use a forward-facing camera. One of the most prominent suppliers of such systems, Mobileye https://www.mobileye.com/, has produced custom chips that use CNNs to detect these objects on the road ahead. To give you an idea of the importance of this sector, in 2017, Intel acquired Mobileye for $15.3 billion. This is not an outlier, and Tesla's famous Autopilot system also relies on CNNs to achieve the same results. In fact, the director of AI at Tesla, Andrej Karpathy https://cs.stanford.edu/people/karpathy/, is a well-known researcher in the field of deep learning. We can speculate that future autonomous vehicles will also use deep networks for computer vision.
• Both Google's Vision API https://cloud.google.com/solutions/image-search-app-with-cloud-vision and Amazon's Rekognition https://aws.amazon.com/rekognition/faqs/ service use deep learning models to provide various computer vision capabilities. These include recognizing and detecting objects and scenes in images, text recognition, face recognition, and so on. 

• If these APIs are not enough, you can run your own models in the cloud. For example, you can use Amazon's AWS Deep Learning AMIs (Amazon Machine Images), https://aws.amazon.com/machine-learning/amis/ , virtual machines that come configured with some of the most popular DL libraries. Google offers a similar service with their Cloud AI, https://cloud.google.com/products/ai/, but they've gone one step further. They created Tensor Processing Units TPUs,( https://cloud.google.com/tpu/ )– microprocessors, optimized for fast neural network operations such as matrix multiplication and activation functions. 
• Deep learning has a lot of potential for medical applications. However, strict regulatory requirements, as well as patient data confidentiality have slowed down its adoption. Nevertheless, we'll identify two areas in which deep learning could have a high impact:
  • Medical imaging is an umbrella term for various non-invasive methods of creating visual representations of the inside of the body. Some of these include Magnetic resonance images (MRIs), ultrasound, Computed Axial Tomography (CAT) scans, X-rays, and histology images. Typically, such an image is analyzed by a medical professional to determine the patient's condition. Computer-aided diagnosis, and computer vision in particular, can help specialists by detecting and highlighting important features of images. For example, to determine the degree of malignancy of colon cancer, a pathologist would have to analyze the morphology of the glands, using histology imaging. This is a challenging task, because morphology can vary greatly. A deep neural network could segment the glands from the image automatically, leaving the pathologist to verify the results. This would reduce the time needed for analysis, making it cheaper and more accessible.
  • Another medical area that could benefit from deep learning is the analysis of medical history records. When a doctor diagnoses a patient's condition and prescribes treatment, they consult the patient's medical history first. A deep learning algorithm could extract the most relevant and important information from those records, even if they are handwritten. In this way, the doctor's job would be made easier, and the risk of errors would also be reduced. 
• Google's Neural Machine Translation API https://arxiv.org/abs/1611.04558 uses – you guessed it – deep neural networks for machine translation.

• Google Duplex is another impressive real-world demonstration of deep learning. It's a new system that can carry out natural conversations over the phone. For example, it can make restaurant reservations on a user's behalf. It uses deep neural networks, both to understand the conversation, and also to generate realistic, human-such as replies. 
• Siri (https://machinelearning.apple.com/2017/10/01/hey-siri.html), Google Assistant, and Amazon Alexa (https://aws.amazon.com/deep-learning/ )rely on deep networks for speech recognition.
• Finally, AlphaGo is an artificial intelligence (AI) machine based on deep learning, which made the news in 2016 by beating the world Go champion, Lee Sedol. AlphaGo had already made the news, in January 2016, when it beat the European champion, Fan Hui. Although, at the time, it seemed unlikely that it could go on to beat the world champion. Fast-forward a couple of months and AlphaGo was able to achieve this remarkable feat by sweeping its opponent in a 4-1 victory series. This was an important milestone, because Go has many more possible game variations than other games, such as chess, and it's impossible to consider every possible move in advance. Also, unlike chess, in Go it's very difficult to even judge the current position or value of a single stone on the board. In 2017, DeepMind released an updated version of AlphaGo called AlphaZero( https://arxiv.org/abs/1712.01815).

With this short list, we aimed to cover the main areas in which deep learning is applied, such as computer vision, natural language processing, speech recognition, and reinforcement learning. This list is not exhaustive, as there are many other uses for deep learning algorithms. Still, I hope this has been enough to spark your interest.