Hello Chetan,
That's very kind of you. Your explanations make me have a better understanding
about the network API. I also watched the video[1] you advised and another
video[2]. But I'm sorry that I can just understand part of it because of my
poor English. So I list my questions as follows, though some of them might have
been explained in videos.
(I learned the network mainly by the code[3], so most of the questions are
based on file[3])
1. I know when the parameter "learningmode" is set to 1, the connections
between each column and cell will keep updating. But how to set parameter
"inferencemode" ? If I have a network sensor-->sp-->tp-->claclassifier, it is
obvious that we should set claclassifier's "inferencemode" to be 1 because we
want to get the output result of claclassifier. My question is how to set sp's
and tp's "inferencemode" (both sp's and tp 's learningmode are 1 for learning
continually)?
2. Does likelihood has the relationship with prediction? The "result"[4] is a
dict, which has two pairs of key-value. One is 1:list1, the other is
actualValues:list2. List1 and list2 are one-to-one correspondence. We get the
actual values in list2 which has the biggest likelihood in list1. And the sum
of list1 equals 1. But I didn't understand how the two lists are calculated.
The bucketIndex gets from scalarEncoder.getBucketIndcex(actualInput) is a
number, and list1's index is a bucket range. What's the corresponding
relationship between bucketIndex and list1? How to define list1's length and
bucket range?
3. In a multiEncoder network, if I want to predict field1, can I know which
fields contribute to field1? Not by swarming.
4. Last time you suggest me to set a parameter to get connection relationship.
I set the 'temporalImp' in file[3] to 'tm_py' but get the error as follows.
Traceback (most recent call last):
File "/newdisk/other/pycharm-community-3.4.1/helpers/pydev/pydevd.py", line
1733, in <module>
debugger.run(setup['file'], None, None)
File "/newdisk/other/pycharm-community-3.4.1/helpers/pydev/pydevd.py", line
1226, in run
pydev_imports.execfile(file, globals, locals) # execute the script
File "/newdisk/nupic/examples/fyj/QK_test/hierarchy_network_demo.py", line
370, in <module>
runDemo()
File "/newdisk/nupic/examples/fyj/QK_test/hierarchy_network_demo.py", line
364, in runDemo
runNetwork(network, numRecords, writer)
File "/newdisk/nupic/examples/fyj/QK_test/hierarchy_network_demo.py", line
307, in runNetwork
network.run(1)
File
"/home/abc/.local/lib/python2.7/site-packages/nupic-0.3.0.dev0-py2.7-linux-x86_64.egg/nupic/engine/__init__.py",
line 669, in run
engine.Network.run(self, n)
File
"/home/abc/.local/lib/python2.7/site-packages/nupic-0.3.0.dev0-py2.7-linux-x86_64.egg/nupic/bindings/engine_internal.py",
line 1142, in run
return _engine_internal.Network_run(self, *args, **kwargs)
File
"/home/abc/.local/lib/python2.7/site-packages/nupic-0.3.0.dev0-py2.7-linux-x86_64.egg/nupic/regions/TPRegion.py",
line 450, in compute
self._compute(inputs, outputs)
File
"/home/abc/.local/lib/python2.7/site-packages/nupic-0.3.0.dev0-py2.7-linux-x86_64.egg/nupic/regions/TPRegion.py",
line 481, in _compute
tpOutput = self._tfdr.compute(buInputVector, self.learningMode,
self.inferenceMode)
File
"/home/abc/.local/lib/python2.7/site-packages/nupic-0.3.0.dev0-py2.7-linux-x86_64.egg/nupic/research/TP_shim.py",
line 82, in compute
numberOfCells = self.connections.numberOfCells()
AttributeError: 'Connections' object has no attribute 'numberOfCells'
[1] https://www.youtube.com/watch?v=QZBtaP_gcn0
[2]https://www.youtube.com/watch?v=gYOwBlVuJDw
[3]https://github.com/numenta/nupic/blob/master/examples/network/hierarchy_network_demo.py
[4]results =classifier.getSelf().customCompute
(recordNum=recordNumber,patternNZ=tpOutput,classification=classDict)
So, can you explain my questions? Thank you so much in advance.
Jing
------------------ ???????? ------------------
??????: "Chetan Surpur";<[email protected]>;
????????: 2015??10??17??(??????) ????2:52
??????: "fuyajing"<[email protected]>;
????: Re: A tp program question
Jing,
> Both spRegion and tpRegion have an attribute "bottomUpOut", which are
> arrays(0 and 1). How to decode the 01 array into a predicted value?
This is what the CLA classifier is used for. It takes these binary output
arrays, and decodes the input value to the encoder that is the most likely
prediction.
> The multiEncoder is not SDR though there is little 1 and much 0.(Or
> multiEncoder is sparse, not distributed? Which explanation is right?)
It is distributed, but not necessarily sparse. It produces sparse
representations only if the inputs to the MultiEncoder are all sparse. Either
way, the output of the SPRegion is sparse and distributed.
> So to top level (for example, classifier), we get a map from final active
> columns index (we call it 'finalColumns') to sourceData.
Correct, this is what the CLA classifier does in essence. You can just use it
on top of the TPRegion to do this classification.
> What's more, I can't understand the code segment in
> nupic/examples/network/hierachy-network-demo.py.(line 267-272)
The `results` dictionary is produced by the CLA Classifier. If you would like
to understand the CLA Classifier better, please see Subutai's recent talk on
how it works [1].
[1] https://www.youtube.com/watch?v=QZBtaP_gcn0
Hope this helps,
Chetan
On Oct 15, 2015, at 12:34 AM, fuyajing <[email protected]> wrote:
And another question: Both spRegion and tpRegion have an attribute
"bottomUpOut", which are arrays(0 and 1). How to decode the 01 array into a
predicted value?
For easier understanding, I want to express my understanding. If I have a wrong
explanation, please tell me. Thank you in advance. :)
For example, each attribute's value can be encoded into a 01 array, by setting
params w, n(or radius, or resolution) , max, min and so on.
A-->1111 0000 0000 0000
B-->0000 1111 0000 0000
C--> 0000 0000 1111 0000
Monday-->111000000000
Tuesday -->011100000000
Thursday-->001110000000
...
Then if there are two attribute need to be encoded, we can just concatenate
them simply, we call it multiEncoder.
AMonday-->1111 0000 0000 0000 111000000000
The multiEncoder is not SDR though there is little 1 and much 0.(Or
multiEncoder is sparse, not distributed? Which explanation is right?) It just
the input of the first spRegion. The out put of spRegion and tpRegion is SDR. (
We can get it from "bottomUpOut"). From the SDR, we can't distinguish which
columns represent for which input bits, right? So to top level (for example,
classifier), we get a map from final active columns index (we call it
'finalColumns') to sourceData. (If we want to predict A, it's a map from
finalColumns to A; if we want to predict Monday, it's a map from finalColumns
to Monday.) I think maybe it's the meaning of decode for HTM. The column
doesn't have a specific correspondence. Moreover, how to initialize the
connection relationship between the input 01 array and first spRegion's columns?
What's more, I can't understand the code segment in
nupic/examples/network/hierachy-network-demo.py.(line267-272)
results =
classifier.getSelf().customCompute(recordNum=recordNumber,patternNZ=tpOutput,classification=classDict)
mostLikelyResult = sorted(zip(results[1], results["actualValues"]))[-1]
How does each element of "results" come out? And I found the lengths of
result[1] and results["actualValues"] are variable lengths.
Looking forward to hear from you at earliest.
Jing
------------------ ???????? ------------------
??????: "??????";<[email protected]>;
????????: 2015??10??15??(??????) ????1:21
??????: "fuyajing"<[email protected]>;
????: A tp program question
HelloI'm using network API to make predictions. The tp_params has an attribute
"cellsPerColumn". My question is: How to get the synapses connection between
columns or cells? Are there any method or code?
Thank you in advance.
Jing
