Timeline for What are the differences between hidden Markov models and neural networks?
Current License: CC BY-SA 3.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 15, 2016 at 20:10 | comment | added | Andrew | Please note that Neural Networks are Turing complete, meaning that with Neural Networks you could perform any calculation that a normal computer can. However, this does not mean that they are ideal for every task. Sometimes I find NN more suitable than HMMs and vice versa. Also, as an alternative (perhaps clearer) view to my previous comment, with RNNs you can imagine mapping the input neurons plus recurring neurons (from the previous timestep) to another space. | |
| Mar 15, 2016 at 20:05 | comment | added | Andrew | The example that comes to mind is the following: given an HMM you can obtain a sequence of elements that belong to the language that the HMM represents. For an RNN to do so, you need to add something over and above it (e.g. try the different inputs and mark an input as a member of a class or otherwise) - although in the case of RNNs you're probably looking at multiple inputs (one after the other) as representing a single "item". HMMs are more naturally suited for the purpose of generating a language. | |
| Mar 15, 2016 at 14:35 | comment | added | rd11 | Hmm. Can you give an example of something you think an HMM can generate, and that you believe can't be generated with an RNN? | |
| Mar 14, 2016 at 20:17 | comment | added | Andrew | Generating a sequence (as in the linked paper) is not the same as generating a language. I suppose that you could apply them to discern between elements of a set and otherwise if you wish, however, a recurrent model can be envisaged as taking a single large input spanning over the individual inputs with recurrence and returning one large output. Not sure if the recurrent Neural Network can give you the outputs without any inputs. | |
| Mar 14, 2016 at 12:22 | comment | added | rd11 | This answer is simply wrong. The Neural Network here is assumed to be feedforward. This is only one class of neural networks. Recurrent models do not simply map single inputs down to a lower-dimensional representation, and they can generate language. See for example arxiv.org/abs/1308.0850 | |
| Apr 6, 2012 at 21:55 | history | edited | Andrew | CC BY-SA 3.0 |
Added on extra sentence to meet OPs question as to whether there are any differences.
|
| Apr 6, 2012 at 20:28 | history | edited | Andrew | CC BY-SA 3.0 |
Improved answer by explaining more clearly some items.
|
| Apr 6, 2012 at 17:30 | comment | added | Phillip Cloud | +1 For the second paragraph. I would like to point out that anyone who clearly understands all the elements of this answer probably wouldn't be asking the original question. It's probably not helpful to mention formal grammars to someone whose post starts with "I'm just getting my feet wet in stats..." The second paragraph here captures the essence of what the OP is asking. Instead of the first paragraph, you might say: an HMM models conditional dependencies of hidden states, where each state has a probability distribution over the observations. | |
| Apr 6, 2012 at 13:57 | history | answered | Andrew | CC BY-SA 3.0 |