Machine Learning in Elixir (Pragmatic Bookshelf)
Hot This:
Most Active This Week
Most Active This Month
Most Active This Year
Getting an error when installing the dependencies at the start of this chapter:
could not compile dependency :exla, "mix compile" failed...
New
Hello @seanmor5 ,
When upgrading Axon to 0.7, evaluation fails with:
** (ArgumentError) argument at position 3 is not compatible with c...
New
Comments to Chapter 11 version B 3.0
@seanmor5
The dependencies from chapter 11 gave errors on 10 march 2024.
I followed the advices...
New
@seanmor5
I am enjoying the book so far, but ran into an Elixir error on the last example in chapter 1:
In my last Livebook cell I have...
New
@seanmor5
When I try the
Nx.Random.uniform_split(new_key, split: {}) function in page 130 I got an undefined function error
** (Undefin...
New
The model training loop on page 273 should visualize the model output after each epoch. Instead, an argument error is reported after the ...
New
@seanmor5
Location: In Chapter 1, on page 14
Description: While attempting to cast the species column to a category in normalized_iris,...
New
@seanmor5
Test data should be scaled using the learned parameters from scaling train data. For example, if train data contains [1, 2, 3,...
New
@seanmor5
Instead of https://github.com/jonathanklosko/meow
it’s https://github.com/jonatanklosko/meow
New
@seanmor5
Definition of batch function in the Data module line
|> Stream.chunk_every(batch_size, :discard)
should be
|> Stream....
New
@seanmor5
For now avg_loss is counting like
{loss, params} ->
{batch_loss, new_params} = step(params, x, y)
avg_loss = Nx.add(Nx....
New
Most Active Last Three Years
@seanmor5
The mutate macro from the Explorer.DataFrame variable does not like variables:
It works without the variable:
New
Running the code snippet of Chapter 2 on page 44 of version B1.0, I get the following error:
Evaluation process terminated - an exceptio...
New
@seanmor5
I don’t know if there’s much you can do about it, but the SSL certificate for the Wine dataset from archive.ics.uci.edu has an...
New
Hey @seanmor5,
I’m having great training accuracy but poor evaluation accuracy for the example in Chapter 1 when following the code in t...
New
@seanmor5
For Explorer.Query to access variables defined outside of the query ^ must be used.
Updated in the example below:
cols = ~w(...
New
@seanmor5
Title: Machine Learning in Elixir (epub so pages different i think)
From book:
Current output:
Diff:
inputs: %{"ir...
New
Page 226
Mix install uses older versins of exla, should 0.6 to work with cuda120
Page 230
targets pipeline in Data module misses |>...
New
@seanmor5
In book:
Actual
Diff-ish
Polars[150 x 5]
New
Version: B1.0
On page 104 the code:
Scholar.Metrics.confusion_matrix(test_targets, test_preds)
throws an error: required :num_classes ...
New
@seanmor5
Title: Machine Learning in elixir: Some problems with chapter 7 in Version B2.0
On 3 january 2024 I downloaded the Cats & ...
New
Hey @seanmor5 ,
Similar to the errata on deprecation on page 44, on page 128:
Nx.random_uniform({})
|> NeuralNetwork.predict(w1, b1,...
New
Some minor nits in the beta version:
“but is often considered it’s own type of machine learning.” → should be “its”
“represents a d...
New
This didn’t seem right to me:
For instance, you can squeeze the values of a feature between 0 and 1 by dividing every individual featur...
New
Hey @seanmor5,
The function given in the book
defn profits(trees) do
trees
|> Nx.pow(4)
|> Nx.negate()
|> Nx.add(Nx.mu...
New
Hello @seanmor5! Thanks a lot for the amazing book and new chapter :purple_heart:
I got a couple of errors when trying to run the exampl...
New
Most Active Over Three Years
Version: B1.0
On page 100 (epub version) the code:
model = Scholar.Clustering.KMeans.fit(train_inputs, num_clusters: 3)
throws an er...
New
Version: B1.0
On page 103 & 104 where the code example is:
Scholar.Linear.LogisticRegression.fit( train_inputs,
train_targets,
num_...
New
Machine Learning in Elixir: Scholar.Clustering.KMeans.fit/2 is undefined (B1.0, Chapter 5, Page 109)
Hey @seanmor5,
On page 109:
model = Scholar.Clustering.KMeans.fit(train_inputs, num_clusters: 3)
results in an UndefinedFunctionError....
New
Title: Machine Learning in Elixir: Learning to Learn with Nx and Axon (6)
“You will sometimes see surprising due to precision issues.”
...
New
Version: B1.0
TL;DR: In page 98 should say two instead of three tensors:
Where it says
Next, you create three random normal tensors: ...
New
“You will sometimes see surprising … due to precision issues.”
Missing word, maybe “consequences” or “effects” ?
Thanks for the great j...
New
Examples in GradFun module will show the following warning with Nx 0.5.3
warning: Nx.Defn.Kernel.inspect_expr/1 is deprecated. Use print...
New
I guess the second log should be : 1-y_pred
New
@seanmor5
Title: Manchine learning with elixir: description page 106
Scholar.Metrics.accuracy(test_targets, test_preds)
do not work, ...
New
Hello @seanmor5 !
On page 180 the link to the onnx model is outdated : https://github.com/onnx/models/blob/main/vision/classification/mo...
New
@seanmor5
In the example:
Nx.tensor(0.0000000000000000000000000000000000000000000001)
is said to be 1.0e-45 but it is actually 1.0e-46
New
@seanmor5
{:scholar, “~> 0.1”} allows Scholar versions greater than 0.1 to be installed. This means that code on page 106 won’t run b...
New
The batch chunking in the CatsAndDogs module in Chapter 8 misses :discard
Should be in two places:
|> Stream.chunk_every(batch_size,...
New
@seanmor5
When running the code on page 16 to create the one hot encoded tensors, I get an Nx error I am not able to make sense of:
** ...
New
Not sure if I did something wrong but it seems like the code should instead be
Scholar.Metrics.Classification.accuracy(test_targets, tes...
New
Book Info
Publisher:
Pragmatic Bookshelf
Get money off!
The Pragmatic Bookshelf
35% off any eBook
Simply use coupon code "devtalk.com" at checkout. See full details here.
Latest
Filter by Type:
Related Portals
Devtalk Sponsors
Practical resources that improve the lives of professional developers.
We build trusted fault-tolerant systems that scale to billions of users.
Catch errors, track performance, monitor hosts and more.
Enabling companies to succeed by building software people love.
Courses that'll move you from confusion to "Aha, now I get it!"