wasshuber

wasshuber

Programming Machine Learning: Help: weird results I don't understand

I encountered something that I can’t explain. Any help, tips, or explanations would be great.

I followed the one hidden layer example with 100 nodes and sigmoid activation function. Works great and I can get to 98.6% accuracy with a learning rate of 1.0, a batch size of 1000, and 100 epochs.

I then decided to exchange the sigmoid activation function with the ReLU. This is not done in the book at this point but it is easy enough to program the ReLU and its derivative. Here is the Python code I used:

def relu(z):
    return np.maximum(0.0,z)
def relu_gradient(z):
    return (z > 0)*1

Works fine as long as one reduces the learning rate which I did reduce to 0.1. It reaches about the same level of accuracy as with the sigmoid. I then did one insignificant change in the gradient of the ReLU. Instead of z > 0 I wrote z >= 0. So the code for the gradient was now:

def relu_gradient(z):
    return (z >= 0)*1

This I thought should not make any difference because how often would z be exactly zero? How often would the weighted sum of all inputs in the floating point format be exactly zero? Perhaps never. Even if it is zero occasionally it should hardly make any big difference. But to my surprise, it makes a profound difference. I can only get to about 95%. Why? Why is there almost 4% difference in accuracy for this insignificant change? There must be something weird happening.

I tried this several times to rule out that somehow the random initialization was unusual. I tried it with different learning rates and different batch sizes. None made any difference in the result. I checked for dead neurons. Found none. If somebody can tell me what is going on here I would really appreciate it.

Most Liked

wasshuber

wasshuber

Turns out it was a bug. Using the nomenclature of the book I was feeding h into the gradient function when I should have fed a into it. With the >= comparison this made all the gradients 1 and thus it acted like the linear activation function. (The linear activation function does produce about 94% accuracy.) Properly using the gradient function produces the expected results. It doesn’t matter if one uses > or >=.

I am happy I found this bug. But this is also part of why your book is so great. Programming it yourself forces one to understand the little details and allows one to change and modify the algorithms at the very core, which leads to much deeper understanding of how this all works.

Here is an insight that my experimentation produced. I tested a bunch of different activation functions including weird piecewise linear ones, periodic ones with sin and cos, combinations thereof etc. It surprised me that many work just as good as ReLU or sigmoid with a single hidden layer. (I intend to extend this experimentation to multiple hidden layers.) For example, it is kind of shocking at first that the absolute-value-function works just as good as ReLU. This kind of makes sense in the biological case. A neuron being a cell would not be completely identical to its neighbor neuron. Neurons in nature would certainly have different activation functions. Perhaps not as different as I experimented with but they would perhaps be noisy and distorted versions of sigmoid or ReLU. It doesn’t matter, it still works fine.

Further, this makes me wonder if perhaps that variation in activation functions in nature is a benefit. I am wondering if folks have tried to make nets where each activation function of each neuron is different. Perhaps that confers a training advantage to the network because not everything behaves in exactly the same way? I will try to explore this question. But first I need to extend the code to allow for multiple hidden layers.

This is one critique I have to make. In my opinion, it would have been better to go further with the code and extend it to multiple hidden layers than to switch to libraries. The point of the book is programming it yourself to allow full unmitigated experimentation. I would have added one or two chapters to extend the code further even if that would have meant leaving out libraries altogether. Numpy should be fast enough to explore multilayer networks on a single average computer.

Where Next?

Popular Pragmatic Bookshelf topics Top

jamis
The following is cross-posted from the original Ray Tracer Challenge forum, from a post by garfieldnate. I’m cross-posting it so that the...
New
AleksandrKudashkin
On the page xv there is an instruction to run bin/setup from the main folder. I downloaded the source code today (12/03/21) and can’t see...
New
rmurray10127
Title: Intuitive Python: docker run… denied error (page 2) Attempted to run the docker command in both CLI and Powershell PS C:\Users\r...
New
AndyDavis3416
@noelrappin Running the webpack dev server, I receive the following warning: ERROR in tsconfig.json TS18003: No inputs were found in c...
New
digitalbias
Title: Build a Weather Station with Elixir and Nerves: Problem connecting to Postgres with Grafana on (page 64) If you follow the defau...
New
Charles
In general, the book isn’t yet updated for Phoenix version 1.6. On page 18 of the book, the authors indicate that an auto generated of ro...
New
tkhobbes
After some hassle, I was able to finally run bin/setup, now I have started the rails server but I get this error message right when I vis...
New
EdBorn
Title: Agile Web Development with Rails 7: (page 70) I am running windows 11 pro with rails 7.0.3 and ruby 3.1.2p20 (2022-04-12 revision...
New
New
roadbike
From page 13: On Python 3.7, you can install the libraries with pip by running these commands inside a Python venv using Visual Studio ...
New

Other popular topics Top

PragmaticBookshelf
A PragProg Hero’s Journey with Brian P. Hogan @bphogan Have you ever worried that your only legacy will be in the form of legacy...
New
PragmaticBookshelf
Design and develop sophisticated 2D games that are as much fun to make as they are to play. From particle effects and pathfinding to soci...
New
DevotionGeo
I know that -t flag is used along with -i flag for getting an interactive shell. But I cannot digest what the man page for docker run com...
New
New
AstonJ
I’ve been hearing quite a lot of comments relating to the sound of a keyboard, with one of the most desirable of these called ‘thock’, he...
New
AstonJ
Just done a fresh install of macOS Big Sur and on installing Erlang I am getting: asdf install erlang 23.1.2 Configure failed. checking ...
New
wmnnd
Here’s the story how one of the world’s first production deployments of LiveView came to be - and how trying to improve it almost caused ...
New
First poster: bot
The overengineered Solution to my Pigeon Problem. TL;DR: I built a wifi-equipped water gun to shoot the pigeons on my balcony, controlle...
New
husaindevelop
Inside our android webview app, we are trying to paste the copied content from another app eg (notes) using navigator.clipboard.readtext ...
New
PragmaticBookshelf
Author Spotlight: VM Brasseur @vmbrasseur We have a treat for you today! We turn the spotlight onto Open Source as we sit down with V...
New

Sub Categories: