Understanding Convolutional Neural Networks • Hacker News Board

Re: Understanding Convolutional Neural Networks

#21

Post by natch » Fri, Jul 03, 2020, 11:29 PM UTC

ironSkillet wrote: post #16

natch wrote: post #14

Earlier quoted context omitted.

These definitions are too vague by half. In a word, useless. “An aspect of the algorithm, a dial” so the same as a parameter then, according to your definition... the only distinction is it changes model production, but in my experience data does that too, so... no clarity here. You make them sound the same to the naive reader. And you misunderstood my suggestion for the article as a request for your help. But thanks…

I agree with your overall sentiment on the "definitions" offered but just fyi your tone is probably considered to be unnecessarily harsh by many.

Thanks for the call out, I’ll reflect on that.

Re: Understanding Convolutional Neural Networks

#22

Post by mjburgess » Sun, Jul 05, 2020, 8:47 AM UTC

natch wrote: post #14

mjburgess wrote: post #5

Earlier quoted context omitted.

Model: the learnt relationship (eg., f(x; a,b) = ax + b) Parameter: an aspect of the model, a dial which is fixed by data (eg., a) Kernel (as used here): a subset of such parameters Algorithm: procedure which accepts data and produces a model Hyperparameter: an aspect of the algorithm, a dial which changes model production Convolution: A convolution of image A and Filter B describes to what degree A is "like" B. Here…

These definitions are too vague by half. In a word, useless. “An aspect of the algorithm, a dial” so the same as a parameter then, according to your definition... the only distinction is it changes model production, but in my experience data does that too, so... no clarity here. You make them sound the same to the naive reader. And you misunderstood my suggestion for the article as a request for your help. But thanks…

I had intended the term 'dial' to indicate that it is set by the practitioner. 'Data' is not.

Yes, both data and hyper-parameters are inputs to the algorithm.

I wasn't trying to offer anything more than a sketch of the terms for someone already semi-informed.

To "define" terms in a way that a person without any experience of the area could understand would require quite a long article.

My goal wasn't to answer you specifically but to take your observation as establishing a plausible interest in others for something like my comment.

Re: Understanding Convolutional Neural Networks

#23

Post by natch » Tue, Jul 07, 2020, 3:19 AM UTC

ww520 wrote: post #19

natch wrote: post #4

Very nice interactive tutorial tool. I wish some of the terms were defined. Hyperparameter? Convolution? Kernel?

The main parameter in ML is θ (theta), as in Y = θ0 + θ1 X1 + θ2 X2 + ..., which are learned using the training data. (X1, X2, ...) are the features. The main goal of ML is to determine these theta parameters to a model so that you can use them to predict result on new data. Hyperparameters in ML is the tuning parameters on the shape and structure of the model, such as the number of features in linear regression abov…

Thanks, very helpful.