How can we realize complex AI systems that reason, learn and act in noisy worlds composed of objects and relations? How can explicit probabilistic models decide autonomously which representation is best for the data? Big Data is no fad. The world is growing at an exponential rate, and so is the size of data collected across the globe.
Data is becoming more meaningful and contextually relevant, breaks new ground for machine learning ML , in particular for deep learning DL , and artificial intelligence AI , and even moves them from research labs to production [1].
The problem has shifted from collecting massive amounts of data to understanding it - turning it into knowledge, conclusions, and actions. Multiple research disciplines, from cognitive sciences to biology, finance, physics, and the social sciences, as well as many companies believe that data-driven and "intelligent" solutions are necessary in order to solve many of their key problems. AI and ML are very much related.
According to, e. It is related to the similar task of using computers to understand human intelligence, but AI does not have to confine itself to methods that are biologically observable. And, the behavior of a machine is not just the outcome of the program, it is also affected by its "body" and the enviroment it is physically embedded in. To keep it simple, however, if you can write a very clever program that has, say, human-like behavior, it can be AI. But unless it is automatically learned from data, it is not ML: ML is the science that is "concerned with the question of how to construct computer programs that automatically improve with experience" , following, e.
So, AI and ML are both about constructing intelligent computer programs , and deep learning, being an instance of machine learning, is no exception. Deep learning [5, 6], which has achieved remarkable gains in many domains spanning object recognition, speech recognition, and control, can be viewed as constructing computer programs, namely programming layers of abstraction in a differentiable way using reusable structures such as convolution, pooling, auto encoders, variational inference networks, and so on.
