Future of the deep learning?
You might not know it, but deep learning already plays a part in our everyday life. When you speak to your phone via Cortana, Siri or Google Now and it fetches information, or you type in the Google search box and it predicts what you are looking for before you finish, you are doing something that has only been made possible by deep learning. Deep learning is part of a broader family of machine learning methods based on learning data representations, as opposed to task-specific algorithms. It also is known as deep structured learning or hierarchical learning. The term Deep Learning was introduced to the machine learning community by Rina Dechter in 1986, and to Artificial Neural Networks by Igor Aizenberg and colleagues in 2000, in the context of Boolean threshold neurons. Deep learning architectures such as deep neural networks, deep belief networks and recurrent neural networks have been applied to fields including computer vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, bioinformatics, drug design and board game programs, where they have produced results comparable to and in some cases superior to human experts.
So, is there any future for deep learning?
Yes, as 2018 progresses, there are a lot of things that are next for deep learning. Instead of thinking of moving forward in one direction, think of expanding outward in many directions. In this article, we will have a look at the many different technologies and additions that we expect to grace in the next couple of years in relation to deep learning. So, let's see the trends that will bring a new revolution for deep learning -
Recognising a face involves recognition of various sub-structures, known as features, such as the eyes, the chin, nostrils, cheek dimples and so on. Eyes, in turn, are broken down into pupils, iris, and cornea. Standard machine learning requires these features to be pointed out to the computer, as so-called supervised learning. In other words, the system has to learn to recognize nostrils, and then noses, before it’s really good at recognizing faces. Deep learning takes this concept a step further. For deep learning, the software is able to reach its own conclusions about layers of intermediate functions that need to be identified. This is known as unsupervised learning. Throw in the fact that you need many layers for it to work properly, and you get the 'deep' bit.
Deep learning for security. More cyber attacks will leverage machine learning to make more autonomous malware, more efficient fuzzing for vulnerabilities, etc. More cyberdefenses will leverage machine learning to respond faster than a human could, detect more subtle intrusions, etc. ML algorithms from opposing camps will fool each other to carry out both attacks and defensive actions.
Dynamic routing of activity will lead to much larger models that may use even less computation to process a single example than current models use today. But overall, massive amounts of computation will continue to be key for AI; whenever we make one model useless computation, we’ll just want to run thousands of models in parallel to learn-to-learn them.
Deep learning will continue to spread out into general culture and we’ll see artists and meme creators using it to do things that we would never have anticipated. We think Alexei Efros’s lab and projects like CycleGAN are the starts of this.
Machine learning tasks involve problems such as manipulating and classifying large numbers of vectors in high-dimensional spaces. The classical algorithms we currently use for solving such problems take time. Quantum computers will likely be very good at manipulating high-dimensional vectors in large tensor product spaces. It is likely that both the development of both supervised and unsupervised quantum machine learning algorithms will hugely increase the number of vectors and their dimensions exponentially more quickly than classical algorithms. This will likely result in a massive increase in the speed at which machine learning algorithms will run.
This technology includes kit like APIs and services through which developers can create more discoverable and intelligent applications. Machine learning APIs will allow developers to introduce intelligent features such as emotion detection; speech, facial, and vision recognition; and language and speech understanding into their applications. The future of this field will be the introduction of deeply personalized computing experiences for all.
Companies building these types of driver-assistance services, as well as full-blown self-driving cars like Google’s, need to teach a computer how to take over key parts or all of driving using digital sensor systems instead of a human’s senses. To do that companies generally start out by training algorithms using a large amount of data.
AI is completely reshaping life sciences, medicine, and healthcare as an industry. Innovations in AI are advancing the future of precision medicine and population health management in unbelievable ways. Computer-aided detection, quantitative imaging, decision support tools and computer-aided diagnosis will play a big role in the years to come.
One of the most popular usage areas of deep learning is voice search & voice-activated intelligent assistants. With the big tech giants have already made significant investments in this area, voice-activated assistants can be found on nearly every smartphone. Apple’s Siri is on the market since October 2011. Google Now, the voice-activated assistant for Android, was launched less than a year after Siri. The newest of the voice-activated intelligent assistants is Microsoft Cortana.
Predicting Natural Disaster
Harvard scientists used Deep Learning to teach a computer to perform viscoelastic computations, these are the computations used in predictions of earthquakes. Until their paper, such computations were very computer intensive, but this application of Deep Learning improved calculation time by 50,000%. When it comes to earthquake calculation, timing is important and this improvement can be vital in saving a life.
Automatic Machine Translation
This is a task where given words, phrase or sentence in one language, automatically translate it into another language. Automatic machine translation has been around for a long time, but deep learning is achieving top results. Text translation can be performed without any pre-processing of the sequence, allowing the algorithm to learn the dependencies between words and their mapping to a new language.
Another popular area regarding deep learning is image recognition. It aims to recognize and identify people and objects in images as well as to understand the content and context. Image recognition is already being used in several sectors like gaming, social media, retail, tourism, etc. This task requires the classification of objects within a photograph as one of a set of previously known objects. A more complex variation of this task called object detection involves specifically identifying one or more objects within the scene of the photograph and drawing a box around them.
Advertising is another key area that has been transformed by deep learning. It has been used by both publishers and advertisers to increase the relevancy of their ads and boost the return on investment of their advertising campaigns. For instance, deep learning makes it possible for ad networks and publishers to leverage their content in order to create data-driven predictive advertising, real-time bidding (RTB) for their ads, precisely targeted display advertising and more.
This is a task where given a corpus of handwriting examples, generate new handwriting for a given word or phrase. The handwriting is provided as a sequence of coordinates used by a pen when the handwriting samples were created. From this corpus, the relationship between the pen movement and the letters is learned and new examples can be generated ad hoc.
This is an interesting task, where a corpus of text is learned and from this model new text is generated, word-by-word or character-by-character. The model is capable of learning how to spell, punctuate, form sentences and even capture the style of the text in the corpus. Large recurrent neural networks are used to learn the relationship between items in the sequences of input strings and then generate text.
Drug discovery and toxicology
A large percentage of candidate drugs fail to win regulatory approval. These failures are caused by insufficient efficacy, undesired interactions, or unanticipated toxic effects. Research has explored the use of deep learning to predict biomolecular target, off-target and toxic effects of environmental chemicals in nutrients, household products, and drugs.
Image colorization is the problem of adding color to black and white photographs. Deep learning can be used to use the objects and their context within the photograph to color the image, much like a human operator might approach the problem. This capability leverage the high quality and very large convolutional neural networks trained for ImageNet and co-opted for the problem of image colorization. Generally, the approach involves the use of very large convolutional neural networks and supervised layers that recreate the image with the addition of color.
Deep Learning is also heavily used in robotics these days. The robots react to people pushing them around, they also get up when falling, and can even take care of pretty elaborate tasks that require gentle and careful.
Finance and Neural Networks
The major fields of finance in which neural networks have been deployed are trading, business analytics, financial operations, product maintenance. In areas of risk assessment, neural networks are undisputed leaders. All kinds of traders can make use of these networks for forecasting and market research purposes. Price data can be thoroughly analyzed and opportunities can be uncovered by detecting not so obvious non-linear interdependencies or patterns which traditional analysis methods fail to do.