The Hangout is full it seems, so I’ll have to stick to the YouTube feed. 

Thanks for doing this!

Pete





On 12 Nov 2013, at 23:53, Matthew Taylor <[email protected]> wrote:

> Hangout: https://plus.google.com/hangouts/_/7ecpjh57bqs47e27f1hqkkcdps
> YouTube: http://youtu.be/rSpYyUN4iP0
> ---------
> Matt Taylor
> OS Community Flag-Bearer
> Numenta
> 
> 
> On Sat, Nov 9, 2013 at 5:21 PM, Matthew Taylor <[email protected]> wrote:
>> At this office hour[1], Subutai is going to lead us through the "CLA
>> Quiz". We'll focus on the spatial pooler. The questions are below.
>> Bring your brains!
>> 
>> **Spatial Pooler / SDR Questions**
>> 
>> 0) Is an untrained CLA spatial pooler just a “random hash” (random
>> mapping from input to output vector)?  Why or why not? What happens to
>> the output of the spatial pooler if you randomly change one bit in the
>> input.
>> 
>> 1) Can you do spatial pooling with small numbers?  For example, is it
>> reasonable to have an SP with 20 columns? If not, why are large
>> numbers important in SDR's?
>> 
>> a) What's the difference between picking "5 columns out of 50" vs "50
>> out of 500"?  Both have 10% sparsity.
>> 
>> b) What's the difference between picking "50 out of 100" vs "50 out of
>> 1000"? Both will output 50 1's.
>> 
>> 2) Suppose the input vector (input to the SP) is 10,000 bits long,
>> with 5% sparsity. What is the right value of coincInputPoolPct? How do
>> you figure this out?
>> 
>> 3) How does the SDR representation of input A in isolation, and input
>> B in isolation, compare with the SDR representation of input A
>> overlapped with B?  Alternatively, how does the representation of a
>> horizontal line and the representation of a vertical line compare with
>> the representation of a cross?
>> 
>> 4) Suppose we have an input vector that is 10,000 bits long.  Suppose
>> the spatial pooler has 500 columns, of which 50 are active at any
>> time.
>> 
>>     a) Can we distinguish many patterns, or a small number? Which
>> patterns are likely to be confused?
>> 
>>     b) What happens to the SDR representation if we add noise to the 
>> patterns?
>> 
>>     c) What happens if we add occlusions?
>> 
>> 5) What are disadvantages of SDR's?
>> 
>> 6) How does online learning happen in the SP?
>> 
>> ---------
>> Matt Taylor
>> OS Community Flag-Bearer
>> Numenta
>> 
>> [1] 
>> https://plus.google.com/b/100642636108337517466/events/crmrf6k58s77hlgk4v30bll8hp8
> 
> _______________________________________________
> nupic mailing list
> [email protected]
> http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org


_______________________________________________
nupic mailing list
[email protected]
http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org

Reply via email to