- Can I use a Nikon F objective with a Olympus OM-D E-M10?
- Origin of the sound / noise made by some stabilized lenses?
- What are “distance fields” and how are they applicable to collision detection?
- How do you manage / collaborate on a project in Unreal with Developers and Designers?
- How create facebook ads based on.user last activity on our website?
- Do “forgiven” felonies still count towards the ending?
- Can't Destroy Storage room
- Is it possible to see Hot Coco and Eggipus Rex leaderboards?
- My pet is a public menace, what did I do wrong?
- AMD ReLive not Recording Fullscreen Games
- How to keep the spawnchunks loaded without generating the nether or end
- How does Trump do character stat graphics on screen?
- Automatically open ICS files in Google Calendar
- Transferring Emails via Thunderbird - Copying Cancels Out
- How can I view my previously scanned checks in Capital One 360?
- How to convert Unix Timestamp to human readable?
- Edit button doesn't show error in the review queue [duplicate]
- When is my chat room most active — in general, not just this week?
- Started monerod on cli but it just hangs, or am I not suppose to see anything happen while downloading ?
- What is everyone doing with Monero for the upcoming BTC fork?
An Artificial Neuron Network (ANN) with an arbitrary number of inputs and outputs
I would like to use ANNs for my problem, but the issue is my inputs and outputs node numbers are not fixed.
I did some google search before asking my question and found that the RNN may help me with my problem. But, all examples which I've found are somehow have defined number of input and output nodes.
So, I'm looking for a strategy, how to make it real or at least some examples, preferable in Keras or PyTorch.
More details about my issue:
I have two inputs lists, where the length of the first one is fixed and equals two, f.e.:
in_1 = [2,2]
but the length of the second list is flexible, the length can be from three to inf, f.e.:
in_2 = [1,1,2,2]
in_2 = [1,1,1,2,2,2,3,3,3]
Also, input lists depend on each other. The first list shows the dimension of the output list. So if in_1 = [2,2], means the output must have a possibility to be reshape to [2,2] form.
Currently, I'm thinking to combine two input list into one:
in = in_1 + in_2 = [2, 2, 1, 1, 2,
The answer may depend on the significance of the length of the input vector or how it originates.
However, the simplest solution is usually to know the largest size input and use that as number of vectors. If the given input has lesser length, you can do the padding with zeros or appropriate symbols. So instead of having a vector [1, 2, 3] and [1, 2, 2, 3] you can have vectors [1, 2, 3, 0] and [1, 2, 2, 3].
The same can apply for output. If output expected is [1, 2, 1] and [1, 3, 4, 1] you can treat the first output as [1, 2, 1, 0]
Isn't this just a hack?
Typically, Neural networks does function approximation. Ideally, it represents vectors (matrices) as input and vectors (matrices) as output. This is why it is always desirable that size of your input vector be fixed.2017-07-17 12:27:18