One can compare deep learning with respect to machine learning as a well structured simple algorithm and deep learning as amplified type of artificial intelligence structure.
Deep learning is a subset of machine learning, and machine learning is a subset of AI, which is an umbrella term for any computer program that does something smart. In other words, all machine learning is AI, but not all AI is machine learning, and so forth [1].
[1] https://skymind.ai/wiki/ai-vs-machine-learning-vs-deep-learning, accessed 19th of June 2019
Just as an example, I would not call this paper https://www.nature.com/articles/nature14539, a hype. There are theoretical reasonings behind that to not being considered a hype, but I think you might just take a look at the paper, and it will provide a much better answer to the question that you have raised.
One can compare deep learning with respect to machine learning as a well structured simple algorithm and deep learning as amplified type of artificial intelligence structure.
Deep learning is a subset of machine learning, and machine learning is a subset of AI, which is an umbrella term for any computer program that does something smart. In other words, all machine learning is AI, but not all AI is machine learning, and so forth [1].
[1] https://skymind.ai/wiki/ai-vs-machine-learning-vs-deep-learning, accessed 19th of June 2019
1) machine learning works on data already provided in from of data sets, tests sets and verification sets. the thing is it works on what it has learn from data set.
2) we have to assign features by our own.
3) if the data set is big and features are less then the chances of under fitting increases.
4) if data is big then computation time increases.
Deep Neural Networks:
1) work like a human brain where neurons are interconnected
2) make decisions on its own and we dont have to provide features manually.
3) if the data is big and features are less then we can use pooling layer in order to avoid under fitting.
4) computational time reduces due to pooling layers.
For me and technically, Deep learning is also machine learning and works exactly in a similar way (hence why the terms are sometimes loosely interchanged). The main difference compared to machine learning is that Deep learning is based on hidden layers to extract more features. Finally, we can never favor one to the other. Because each method can be powerfull on one problem and less powerfull to on another one.
Machine learning uses algorithms to parse data, learn from that data, and make informed decisions based on what it has learned. Deep learning structures algorithms in layers to create an “artificial neural network” that can learn and make intelligent decisions on its own. Deep learning is a sub field of machine learning