My understanding is that Deep Learning brings concepts from research in neural network (such as layers, distribution, physical grounding, and hierarchy) into machine learning. Technically, it is not completely you. Practically, research in neural networks (and especially biologically-inspired cognitive architectures) has done quite a lot to uncover the biological principles that govern cognition. The work of Randy O'Reilly, Michael J. Frank, and Chris Eliasmith is particularly noteworthy. And I believe it does bring some fresh air and new perspectives into the field of ML.
Deep Learning is a way of learning everything you need for a classification or clustering problem with neural facts and models. But it requires a good amount of computational power to get away its ramification complexity. If you provide this huge clusters and GPU facilities to your algorithm it is reasonable to obtain promising results for the problem. It is what the Google does currently. They are devoting clusters of computers to learn visual concepts from their image search engine with Deep Learning algorithms. On the other side of the spectrum it is not possible to find this much power as a simple company or institution. Therefore, other methods like hand crafted features and kernel machines also need to be considered even with simple Bag of Words features. There are also some papers saying that well crafted BoW approaches possibly give overrated results in relation to deep learning methods in some of the problems in especially computer vision. Beside all those criticism it is certainly most ground breaking learning tool of the last age of ML with its neuroscientific promise as well.
Here is one example paper :http://www.stanford.edu/~acoates/papers/coatesng_nntot2012.pdf
Deep learning is machine’s ability to observe the patterns to pile the information to use for decision making or assessing future expected outcome. Mankind has been working on robots since long with no much break through invention. Deep learning is hot topic in research now a days and researcher are hoping to bring fruit of past hardworking in the shape of machine leaning. It is a milestone to get the most out of artificial intelligence. Now this powerful machine learning is being use in image and speech recognition along with decoding natural language processing. Many of the companies such as Google, Facebook and Microsoft have capitalized on the concept for commercial use. The goal of deep learning is to develop a self learning mechanism build on huge data sets for complex interpretations. It is not about copying the brain rather it about educating machines to sense and act contextually.
For more information please visit my article in LinkedIn.
Deep learning is one of the many tools used to solve a problem. History in AI has shown that hype (just like the one we are experiencing with deep learning) can lead to disillusionment and overreaction against the field. Limiting yourself to one paradigm will only slow your progress in the field