grossvogel

grossvogel

Machine Learning in Elixir: Average loss calculation in SGD example (page 88)

The calculation of average loss doesn’t seem right to me:

avg_loss = Nx.add(Nx.mean(batch_loss), loss) |> Nx.divide(j + 1)

I believe loss is the average loss returned by the previous iteration, which includes j samples so far, so I would think we’d need to weight that by multiplying by j before dividing by j + 1… something like this?

avg_loss = Nx.add(Nx.mean(batch_loss), Nx.multiply(loss, j)) |> Nx.divide(j + 1)

or am I confusing myself?

Where Next?

Popular Pragmatic Bookshelf topics Top

leonW
I ran this command after installing the sample application: $ cards add do something --owner Brian And got a file not found error: Fil...
New
jimschubert
In Chapter 3, the source for index introduces Config on page 31, followed by more code including tests; Config isn’t introduced until pag...
New
mcpierce
@mfazio23 I’ve applied the changes from Chapter 5 of the book and everything builds correctly and runs. But, when I try to start a game,...
New
abtin
page 20: … protoc command… I had to additionally run the following go get commands in order to be able to compile protobuf code using go...
New
adamwoolhether
When trying to generate the protobuf .go file, I receive this error: Unknown flag: --go_opt libprotoc 3.12.3 MacOS 11.3.1 Googling ...
New
hgkjshegfskef
The test is as follows: Scenario: Intersecting a scaled sphere with a ray Given r ← ray(point(0, 0, -5), vector(0, 0, 1)) And s ← sphere...
New
HarryDeveloper
Hi @venkats, It has been mentioned in the description of ‘Supervisory Job’ title that 2 things as mentioned below result in the same eff...
New
oaklandgit
Hi, I completed chapter 6 but am getting the following error when running: thread 'main' panicked at 'Failed to load texture: IoError(O...
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
brianokken
Many tasks_proj/tests directories exist in chapters 2, 3, 5 that have tests that use the custom markers smoke and get, which are not decl...
New

Other popular topics Top

First poster: bot
zig/http.zig at 7cf2cbb33ef34c1d211135f56d30fe23b6cacd42 · ziglang/zig. General-purpose programming language and toolchain for maintaini...
New
DevotionGeo
I know that these benchmarks might not be the exact picture of real-world scenario, but still I expect a Rust web framework performing a ...
New
AstonJ
There’s a whole world of custom keycaps out there that I didn’t know existed! Check out all of our Keycaps threads here: https://forum....
New
PragmaticBookshelf
As digital systems increasingly run the world, mastery of the recurring patterns of software development risk is the key to fast and effe...
New
PragmaticBookshelf
Author Spotlight Mike Riley @mriley This month, we turn the spotlight on Mike Riley, author of Portable Python Projects. Mike’s book ...
New
New
Margaret
Hello everyone! This thread is to tell you about what authors from The Pragmatic Bookshelf are writing on Medium.
1147 29994 760
New
PragmaticBookshelf
Write Elixir tests that you can be proud of. Dive into Elixir’s test philosophy and gain mastery over the terminology and concepts that u...
New
xiji2646-netizen
Woke up to this today: Claude Code’s complete source code exposed via npm source map. Not a snippet. All 512,000 lines. 1,900 TypeScript ...
New
AstonJ
We’ve talked about his book briefly here but it is quickly becoming obsolete - so he’s decided to create a series of 7 podcasts, the firs...
New

Sub Categories: