Can someone explain to me the difference between machine learning and deep learning? Is it possible to learn deep learning without knowing machine learning?
$\begingroup$ The difference is that deep learning includes implicitly representation learning in their models. $\endgroup$– freesoulFeb 11, 2019 at 9:21
Deep learning is a specific variety of a specific type of machine learning. So it's possible to learn about deep learning without learning all of machine learning, but it requires learning some machine learning (because it is some machine learning).
Machine learning refers to any technique that focuses on teaching the machine how it can learn statistical parameters from a large amount of training data. One particular type of machine learning is artificial neural networks, which learn a network of nonlinear transformations that can approximate very complicated functions of wide arrays of input variables. Recent advances in artificial neural networks have to do with how to train deep neural networks, which have more layers than normal and also special structure to deal with the challenges of learning more layers.
Deep learning is one form of machine learning.
Deep learning refers to learning with deep neural networks, essentially networks with many layers.
Neural networks are one group of many forms of machine learning:
- Neural Networks
- Decision Trees and Random Forests
- Support Vector Machines
- Bayesian Approaches
- k-nearest neighbors
First, in most condition machine learning actually refers traditional/classical machine learning, and deep learning is specifically referring multi-layered neural network, and neural network is one of the machine learning approach.
Second, Machine learning especially supervised machine learning requires engineers to design and predefine features manually, which are used to represent the data in numerical way. Such as we can represent animals with three features such as the number of eyes, the number of legs and the number of heads. The data [2,4,1] representing an animal with 2 eyes, 4 legs and 1 head. In this scenario, the feature is extracted by us, because we have knowledge on animals, and we think these features can represent animals. However, instead of hand-crafting features the deep learning learn the features automatically.
Third, when someone say machine learning he is saying algorithm, such as naive bayes, decision tree, linear regression etc. However, the deep learning is more related to the framework and architecture such as RNN, CNN, Transformer etc.
Fourth, it is possible to start deep learning without knowing machine learning, sources from internet like Andrew Ng's course usually covers most topic you should know in deep learing. Try search Andrew Ng, I think he is really good!
$\begingroup$ This is a good answer that emphasizes that in traditional ML approaches we usually need some form of "feature engineering" (which is a term that you may add to your answer). However, note that when we say deep learning we are not just referring to the architecture but also the algorithms, in particular, gradient descent and back-propagation, which are typically the algorithms used. See also this answer. $\endgroup$– nbroJan 28, 2021 at 16:48
When I started Machine Leraning chapters in book used to look like this
- Linear models
- Logestic Regression
- Neural Network
- Decision Tress and Random Forest
- Boosting and Bagging
- SVD and SVM
II) UnSupervised Learning:
- Gaussian Mixture Model
- DB Scan
III) ReInforment Learning:
All of a sudden chapter I>2>b created a sub-field of its own . Well to know why, let me tell you a bit of history.
Machine learning word was coined in 1959 by Arthur Samuel to signify that
machines were able to learn from data than explicit instruction. Initally it was broken into two groups based on if th approach required label data or not(ie regression, classification), then they realised we can cassify by clustering too which gave birth to unsupervised. And word reinforment learning was born inspired by areas of game theory. Lets keep those details aside for later.
Coming to deep learnign, the word
deep learning came very recently, as recent as 2008 from a Geoff Hinton conference. There people started using it to indicate a very deep neural network architecture used in a paper presented by Geoff Hinton and from then onwards it kind of became as a new way of classifying machine learning besides
reinforcement.(Disc: There may be odd reference of calling NN as DL before this but not so popular and acceptable prior to this)
Well I sometimes feel the name
deep learning is somewhat misnomer, it would have been better of if it was named as
neural learning or to stress on depth maybe
deep neural learning. If you are new you might be wondering what depth I am talking about, the entire word deep came from the fact that neural network (thanks the availability of high processing abilities of GPUs) were now able to train successfully on multiple layers. The word deep can also be loosely used to include other non-neural network areas of machine learning which requires lots of computation like
deep belief net or
recurrent net. To be precise the units of the networks today are no longer a mere
neuron or a
perceptron, it can be
GRU or a
capsule, so I guess word
deep now makes more sense than before.
Deep Learning is subset of Machine Learning.
Machine learning and Deep learning both are not two different things. Deep learning is one of the form of machine learning. The level of layers in Neural network are more and more in depth learning is part of Deep learning.
“Deep learning is a particular kind of machine learning that achieves great power and flexibility by learning to represent the world as nested hierarchy of concepts, with each concept defined in relation to simpler concepts, and more abstract representations computed in terms of less abstract ones.”