Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
This question does not appear to be about programming within the scope defined in the help center.
Closed 5 years ago.
Improve this question
I practiced already some machine learning aspects, and developed some small projects. Nowadays some blogs, articles, open posts talk about deep learning. I get interested to see practically what the difference between machine learning and deep learning is, and maybe to learn a new approaches/ techniques called deep learning. I read few blogs, but conceptually I see that deep learning is a subset of machine learning, and it’s nothing more than Neural networks with multiple layers!!
I am however stunned and perplexed to recognize if it is the only difference between machine learning and deep learning !!!
What is the merit to think of deep learning and not machine learning if we want only talk about neural networks? so if it is, why not call it neural networks, or deep neural networks to distinguish some classification ?
Is there a real difference than that I mentioned?
Does there any practical example showing a significant difference letting us to make these different notions?
Deep learning is set of ML patterns and tactics to increase accuracy of classical ML algorithms, like MLP, Naïve Bayes classifier, etc.
One of the earliest and easiest of such tactics – adding hidden layers to increase network’s learning capacity. One of recent - convolutional autoencoder
Related
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
Disclaimer: I also posted this question on CrossValidated but it is not receiving any attention. If this is not the place for it I will gladly remove it.
As I understand it, the only difference between them is the way the two networks are trained. Deep autoencoders are trained in the same way as a single-layer neural network, while stacked autoencoders are trained with a greedy, layer-wise approach. Hugo Larochelle confirms this in the comment of this video. I wonder if this is the ONLY difference, any pointers?
The terminology in the field isn't fixed, well-cut and clearly defined and different researches can mean different things or add different aspects to the same terms. Example discussions:
What is the difference between Deep Learning and traditional Artificial Neural Network machine learning? (some people think that 2 layers is deep enough, some mean 10+ or 100+ layers).
Multi-layer perceptron vs deep neural network (mostly synonyms but there are researches that prefer one vs the other).
As for AE, according to various sources, deep autoencoder and stacked autoencoder are exact synonyms, e.g., here's a quote from "Hands-On Machine Learning with Scikit-Learn and TensorFlow":
Just like other neural networks we have discussed, autoencoders can
have multiple hidden layers. In this case they are called stacked
autoencoders (or deep autoencoders).
Later on, the author discusses two methods of training an autoencoder and uses both terms interchangeably.
I would agree that the perception of the term "stacked" is that an autoencoder can extended with new layers without retraining, but this is actually true regardless of how existing layers have been trained (jointly or separately). Also regardless of the training method, the researches may or may not call it deep enough. So I wouldn't focus too much on terminology. It can stabilize some day but not right now.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
As per Pedro Domingos in his famous paper "A Few Useful Things to Know about Machine Learning" he writes Machine learning systems automatically learn programs from data.
But from my experience we r giving algorithms like ANN or SVM etc.
My question is how it is automating automation?
Could someone put some light with example.
When you develop a machine learning algorithm, with ANN or SVM or whatever, you don't say to your programming how to solve your problem, you are telling him how to learn to solve the problem.
SVM or ANN are ways to learn a solution to a problem, but not how to solve a problem.
So when people say "Machine learning systems automatically learn programs from data", they are saying that you never programmed a solution to your problem, but rather letting the computer learning to do so.
To quote wikipedia : "Machine learning is a field of computer science that gives computers the ability to learn without being explicitly programmed"
https://en.wikipedia.org/wiki/Machine_learning
[Edit]
For example let's take one of the most simple machine learning algorithm, the linear regression in a 2D space.
The aim of this algorithm is to learn a linear function given a dataset of (x,y), so when you given your system a new x you get an approximation of what the real y would be.
But when you code a linear regression you never specify the linear function y = ax+b. What you code is a way for the program to deduce it from the dataset.
The linear function y=ax+b is the solution to your problem, the linear regression code is the way you are going to learn that solution.
https://en.wikipedia.org/wiki/Linear_regression
Machine Learning development helps to improve business operations as well as improve business scalability. A number of ML algorithms and artificial intelligence tools have gained tremendous popularity in the community of business analytics. There has been a rise in machine learning market due to faster and cheaper computational processing, easy availability of data as well as affordable data storage.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 9 years ago.
Improve this question
I have learned several classifiers in Machine learning - Decision tree, Neural network, SVM, Bayesian classifier, K-NN...etc.
Can anyone please help to understand when I should prefer one of the classifier over other - for example - in which situation(nature of data sets, etc) I should prefer decision tree over neural net OR which situation SVM might work better than Bayesian ??
Sorry if this is not a good place to post this question.
Thanks.
This is EXTREMELY related to the nature of the dataset. There are several meta-learning approaches that will tell you which classifier to use, but generaly there isn't a golden rule.
If you're data is easily separable (easy to distinguish entries from different classes), perhaps decision-trees or SVMs (with a linear kernel) are good enough. However, if your data needs to be transformed into other [higher] dimensional spaces, kernel-based classifiers might work well, such as RBF SVMs. SVMs also work better with non-redundant, independent features. When combinations between features are needed, artificial neural networks and bayesian classifiers work good as well.
Yet again, this is highly subjective and strongly depends on your feature set. For instance, having a single feature that is highly correlated with the class might determine which classifier works best. That said, overall, the no-free-lunch theorem says that no classifier is better for everything, but SVMs are generally regarded as the current best bet on binary classification.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 3 years ago.
Improve this question
I am new at the domain of machine learning and i have noticed that there are a lot of algorithms/ set of algorithms that can be used: SVM, decision trees, naive bayes, perceptron etc...
That is why I wonder which algorithm should one use for solving which issue? In other words which algorithm solves which problem class?
So my question is if you know a good web site or book that focuses on this algorithm selection problematic?
Any help would be appreciated. Thx in advance.
Horace
Take Andrew Ng's machine learning course on coursera. It's beautifully put together, explains the differences between different types of ML algorithm, gives advice on when to use each algorithm, and contains material useful for practioners as well as maths if you want it. I'm in the process of learning machine learning myself and this has been by far the most useful resource.
(Another piece of advice you might find useful is to consider learning python. This is based on a mistake I made of not starting to learn python at an earlier stage and ruling out the many books, web pages, sdks, etc that are python based. As it turns out, python is pretty easy to pick up, and from my own personal observations at least, widely used in the machine learning and data science communities.)
scikit-learn.org published this infographic, that can be helpful, even when you're not using sklearn library.
#TooTone: In my opinion Machine Learning in Action could help the OP with deciding on which technique to use for a particular problem, as the book gives a clear classification of the different ML algorithms and pros, cons, and "works with" for each of them. I do agree the code is somewhat hard to read, especially for people not used to matrix operations. There is years of research condensed into a 10 line Python program, so be prepared that understanding it will take a day (for me at least).
It is very hard answer the question “which algorithm for which issue?”
That ability comes with a lot of experience and knowledge. So I suggest, you should read few good books about machine learning. Probably, following book would be a good starting point.
Machine Learning: A Probabilistic Perspective
Once you have some knowledge about machine learning, you can work on couple of simple machine learning problems. Iris flower dataset is a good starting point. It consists of several features belonging to three types of Iris species. Initially develop a simple machine learning model (such as Logistic Regression) to classify Iris species and gradually you could move to more advanced models such as Neural Networks.
As a simple starting place I consider what inputs I have and what outputs I want, which often narrows down choices in any situation. For example, if I have categories, rather than numbers and a target category for each input, decision trees are a good idea. If I have no target, I can only do clustering. If I have numerical inputs and a numerical output I could use neural networks or other types of regression. I could also use decision trees that generate regression equations. There are further questions to be asked after this, but it's a good place to start.
Following DZone Refcard might also helpful .. http://refcardz.dzone.com/refcardz/machine-learning-predictive. But you will have to dig in to each in detail eventually.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
This question does not appear to be about programming within the scope defined in the help center.
Closed 1 year ago.
Improve this question
Where is ANN classification (regression) better than SVM? Some real-world examples?
There are many applications where they're better, many applications where they're comparable, many applications where they are worse. It also depends on who you ask. It is hard to say this type of data or that type of data/application.
An example where ANN, in particular convolutional neural networks, work better than SVMs would be digit classification on MNIST. Another such case is the work of Geoff Hinton's group on speech recognition using Deep Belief Networks
Recently I have read a paper of proving the theoretical equivalence between ANN and SVM. However, ANN is usually slower than SVM.
I am just finishing some out-of-the-box comparison between support vector machines and neural networks on several popular regression- and classification datasets - first results in short: svms learn fast and predict slow - neural networks learn slow but predict fast and have very lightweight models. Concerning accuracy/loss, both methods seem to be on par.
It will largely depend as both have different tradeoffs and design criteria. There has been some work to show the relationship and some say equivalence as seen in other answers to this question. Below is another reference which draws links between these two techniques in machine learning:
Ronan Collobert and Samy Bengio. 2004. Links between perceptrons, MLPs
and SVMs. In Proceedings of the twenty-first international
conference on Machine learning (ICML '04). ACM, New York, NY, USA,
23-. DOI: https://doi.org/10.1145/1015330.1015415