https://medium.com/@UdacityINDIA/difference-between-machine-learning-deep-learning-and-artificial-intelligence-d005ae5f23c

I hope it is useful for you the attached file:

Thanks Mokhtar A. Alworafi

I think this link is useful

https://blogs.nvidia.com/blog/2016/07/29/whats-difference-artificial-intelligence-machine-learning-deep-learning-ai/

Thanks Dhyaa Allban

Generally speaking, Machine learning refers to the application of artificial intelligence (AI) for providing systems with the ability to learn automatically based on explicit programming. By contrast, Deep learning also known as deep structured learning or hierarchical learning is part of machine learning methods whereby the learning data representations are not monitored by task-specific algorithms ; rather, computer programs can access data and use it to learn for themselves. In other words, deep learning involves networks which are capable of learning in an unsupervised manner from the data that is unstructured or unlabeled.

Short and sweet Zinah !!!

Deep learning is as the word "deep" a depth based network for flow of data and on the way either extracts features as Convolutional network (CNN) does OR does regression like Neural networks (ANN) .

While Machine learning is not a network per se but is a algorithmic approach based on heuristic learning .

The commonality is : Both are #s based hence I would think the "BIG DATA" or "Data analytics " is the backbone

https://medium.com/@UdacityINDIA/difference-between-machine-learning-deep-learning-and-artificial-intelligence-d005ae5f23c

thi link good for question

https://www.researchgate.net/deref/https%3A%2F%2Fblogs.nvidia.com%2Fblog%2F2016%2F07%2F29%2Fwhats-difference-artificial-intelligence-machine-learning-deep-learning-ai%2F

There are two major issues in applied Deep Learning.

1 - The first being that computationally , it's exhaustive. Normal CPU's require a lot of time to perform even the basic computation/training with Deep Learning. GPU's are thus recommended however, even they may not be enough in a lot of situations. Typical deep learning models don't support the theoretical time to be in Polynomials. However, if we look at the relatively simpler models in ML for the same tasks, too often we have mathematical guarantees that training time required for such simpler Algorithms is in Polynomials. This, for me, at least is probably the biggest difference.

2 - Another Issue which may be a little bit controversial to young deep learning enthusiasts is that Deep Learning algorithms lack theoretical understanding and reasoning. Deep Neural Networks have been successfully used in a lot of situations including Hand writing recognition, Image processing, Self Driving Cars, Signal Processing, NLP and Biomedical Analysis. In some of these cases, they have even surpassed humans. However, that being said, they're not under any circumstance, theoretically as sound as most of Statistical Methods.

Machine learning is a challenging area of computer science and engineering and there are many different approaches to building machine learning systems. As yet there is no formal classification of these different approaches but in his book The Master Algorithm1 Pedro Domingos of the University of Washington provides a coherent and accessible overview to the different methods currently being pursued.

Deep learning is revolutionizing speech and natural language technologies since it is offering an effective way to train systems and obtaining significant improvements. The main advantage of deep learning is that, by developing the right architecture, the system automatically learns features from data without the need of explicitly designing them.

Also, Deep learning was first introduced in standard statistical systems. By now, end-to-end neural MT systems have reached competitive results. This special issue introductory paper addresses how deep learning has been gradually introduced in MT.

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.

Deep learning models are vaguely inspired by information processing and communication patterns in biological nervous systems yet have various differences from the structural and functional properties of biological brains, which make them incompatible with neuroscience evidences.

Thanks Yehya A. Salih

In addition to above information you can return to the following link :

https://books.google.iq/books?hl=ar&lr=&id=-eqpCAAAQBAJ&oi=fnd&pg=PA2&dq=machine+learning+approaches+and+Deep+learning+approaches&ots=Wl2OMy8Bl8&sig=KFaUU4vi_zPwiJu-QPi1xRoT4BA&redir_esc=y#v=onepage&q=machine%20learning%20approaches%20and%20Deep%20learning%20approaches&f=false.

You most welcome dear Zinah Hussein,,,

With my best wishes.

Dr. Yehya

Automated learning is one type of Artificial Intelligence, which allows software applications to become more accurate in predicting results without explicitly programming them.

Deep learning is a branch of machine learning. A field in which the computer tests logarithms and programs and learns to improve and develop it by itself

Machine learning is not new and its roots date back to the mid-20th century. Where English athlete Alan Turing proposed a vision of artificial intelligence (the machine learning)

Deep learning is a sub field of machine learning the common technique in DL CNN

I agree with Sarah Hussein

Thanks Reza Biria

Thanks Aparna Sathya Murthy

Thanks Mhsen Alwan Mohammed

Thanks Batool Ghali

Thanks Sarah Hussein

Thanks Djaafar Zemali

Thanks Mohammed Hamzah Abed

We can conclude that deep learning is nothing but large-scale neural networks that have large data and require supercomputers. Although preliminary studies have focused on non-censored means, the latest developments in this area have focused on deep training and neural network models using reverse algorithms , The most popular techniques in this area are:

- Multilayer receiver networks

- Neural networks

- Neural networks of long-term short-term memory.

The links below can provide you with more detailed information on the issue.

https://www.sciencedirect.com/science/book/9780128015223

Chapter Part 3. Machine learning and deep learning networks

Evolutionary Approach to Machine Learning and Deep Neural Networks

https://www.asee.org/public/conferences/78/papers/20509/view