Machine Learning in Elixir (Pragmatic Bookshelf)

Hot This:
PragmaticBookshelf
Backend Developer Forum>Learning Resources

Machine Learning in Elixir
Leverage Elixir and the Nx ecosystem to build intelligent applications that solve real-world problems in computer vision, natural language processing, and more.

Sean Moriarity @seanmor5

edited by Tammy Coron @Paradox927

Stable Diffusion, ChatGPT, Whisper—these are just a few examples of incredible applications powered by developments in machine learning. Despite the ubiquity of machine learning applications running in production, there are only a few viable language choices for data science and machine learning tasks. Elixir’s Nx project seeks to change that. With Nx, you can leverage the power of machine learning in your applications, using the battle-tested Erlang VM in a pragmatic language like Elixir. In this book, you’ll learn how to leverage Elixir and the Nx ecosystem to solve real-world problems in computer vision, natural language processing, and more.

The Elixir Nx project aims to make machine learning possible without the need to leave Elixir for solutions in other languages. And even if concepts like linear models and logistic regression are new to you, you’ll be using them and much more to solve real-world problems in no time.

Start with the basics of the Nx programming paradigm—how it differs from the Elixir programming style you’re used to and how it enables you to write machine learning algorithms. Use your understanding of this paradigm to implement foundational machine learning algorithms from scratch. Go deeper and discover the power of deep learning with Axon. Unlock the power of Elixir and learn how to build and deploy machine learning models and pipelines anywhere. Learn how to analyze, visualize, and explain your data and models.

Discover how to use machine learning to solve diverse problems from image recognition to content recommendation—all in your favorite programming language.

Sean Moriarity is author of Genetic Algorithms in Elixir: Solve Problems using Evolution, co-creator of the Nx library, and creator of the Axon deep learning framework. Sean’s interests include mathematics, machine learning, and artificial intelligence.

Don’t forget you can get 35% off with your Devtalk discount! Just use the coupon code “devtalk.com" at checkout :+1:

#nx/elixir#pragprog#machine-learning#published-book/book-machine-learning-in-elixir
18 1170 7

Latest Threads About This Book Top

dmitrykleymenov
PragProg Customers

Machine Learning in Elixir: Chapter 4. Bug with avg_loss counting
@seanmor5 For now avg_loss is counting like {loss, params} -> {batch_loss, new_params} = step(params, x, y) avg_loss = Nx.add(Nx....
/book-machine-learning-in-elixir#errata
0 12 0
New
code-of-kai
PragProg Customers

Chapter 1: Dataframe Column Reference Bug (updated)
@seanmor5 Location: In Chapter 1, on page 14 Description: While attempting to cast the species column to a category in normalized_iris,...
/book-machine-learning-in-elixir#errata
0 80 1
New
bosko
PragProg Customers

Machine Learning in Elixir P1.0: Chapter 10 (page 224) definition of batch function
@seanmor5 Definition of batch function in the Data module line |> Stream.chunk_every(batch_size, :discard) should be |> Stream....
/book-machine-learning-in-elixir#errata
0 24 0
New
ahamez
PragProg Customers

Machine Learning in Elixir: Chapter 1 doesn't work with Axon 0.7 (page 26)
Hello @seanmor5 , When upgrading Axon to 0.7, evaluation fails with: ** (ArgumentError) argument at position 3 is not compatible with c...
/book-machine-learning-in-elixir#errata
9 219 2
New
CoderDennis
PragProg Customers

Machine Learning in Elixir: chapter 7 CNN model accuracy no better than MLP (page 160)
When training the cnn_model, I get the following output: Epoch: 0, Batch: 150, accuracy: 0.4985513 loss: 7.6424022 Epoch: 1, Batch: 163,...
/book-machine-learning-in-elixir
0 26 3
New
daneroo
PragProg Customers

Machine Learning in Elixir: Code Repository
Machine Learning in Elixir: Code Repository Can we get a link to a GitHub repository with all erratas for the examples patched, Then we...
/book-machine-learning-in-elixir#suggestion
2 51 0
New
hugobarauna
PragProg Customers

Machine Learning in Elixir: wrong GitHub repo URL (page 92)
@seanmor5 Instead of https://github.com/jonathanklosko/meow it’s https://github.com/jonatanklosko/meow
/book-machine-learning-in-elixir#errata
0 22 0
New
shaolang
PragProg Customers

Machine Learning in Elixir: B5 Page 105 Incorrect application of min_max_scale
@seanmor5 Test data should be scaled using the learned parameters from scaling train data. For example, if train data contains [1, 2, 3,...
/book-machine-learning-in-elixir#errata
0 21 1
New
zacksiri
PragProg Customers

Machine Learning in Elixir: Nx.Random.uniform_split wrong arguments 130
@seanmor5 When I try the Nx.Random.uniform_split(new_key, split: {}) function in page 130 I got an undefined function error ** (Undefin...
/book-machine-learning-in-elixir#errata
1 166 0
New
glappen
PragProg Customers

Machine Learning in Elixir: Error running last example in Chapter 1 (Evaluating the Trained Model)
@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...
/book-machine-learning-in-elixir#errata
2 190 2
New

Most Active This Week Top

Most Active This Month Top

dmitrykleymenov
PragProg Customers

Machine Learning in Elixir: Chapter 4. Bug with avg_loss counting
@seanmor5 For now avg_loss is counting like {loss, params} -> {batch_loss, new_params} = step(params, x, y) avg_loss = Nx.add(Nx....
/book-machine-learning-in-elixir#errata
0 12 0
New

Most Active This Year Top

PragmaticBookshelf
Backend Developer Forum>Learning Resources

Machine Learning in Elixir
Leverage Elixir and the Nx ecosystem to build intelligent applications that solve real-world problems in computer vision, natural languag...
#nx/elixir#pragprog#machine-learning#published-book/book-machine-learning-in-elixir
18 1170 7
New
SlowburnAZ
PragProg Customers

Machine Learning in Elixir:Error installing EXLA dependency - Page 25
Getting an error when installing the dependencies at the start of this chapter: could not compile dependency :exla, "mix compile" failed...
/book-machine-learning-in-elixir#errata
0 1017 10
New
ahamez
PragProg Customers

Machine Learning in Elixir: Chapter 1 doesn't work with Axon 0.7 (page 26)
Hello @seanmor5 , When upgrading Axon to 0.7, evaluation fails with: ** (ArgumentError) argument at position 3 is not compatible with c...
/book-machine-learning-in-elixir#errata
9 219 2
New
augusto1024
PragProg Customers

Machine Learning in Elixir: Chapter 7 - Low accuracy and weight matrix full of NaNs in MLP example
I’m going through the MLP Livebook for identifying cats and dogs, and after training the MLP model and testing it, I get an accuracy of 4...
/book-machine-learning-in-elixir#question
8 369 2
New
pieteeken
PragProg Customers

Machine Learning in Elixir: comments on chapter 11, version B 3.0
Comments to Chapter 11 version B 3.0 @seanmor5 The dependencies from chapter 11 gave errors on 10 march 2024. I followed the advices...
/book-machine-learning-in-elixir#errata
1 342 1
New
glappen
PragProg Customers

Machine Learning in Elixir: Error running last example in Chapter 1 (Evaluating the Trained Model)
@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...
/book-machine-learning-in-elixir#errata
2 190 2
New
zacksiri
PragProg Customers

Machine Learning in Elixir: Nx.Random.uniform_split wrong arguments 130
@seanmor5 When I try the Nx.Random.uniform_split(new_key, split: {}) function in page 130 I got an undefined function error ** (Undefin...
/book-machine-learning-in-elixir#errata
1 166 0
New
jshprentz
PragProg Customers

Machine Learning in Elixir: Chapter 12, B 3.0: Image tensor is wrong shape for Kino.Image.new (pages 271-273)
The model training loop on page 273 should visualize the model output after each epoch. Instead, an argument error is reported after the ...
/book-machine-learning-in-elixir#errata
0 165 0
New
code-of-kai
PragProg Customers

Chapter 1: Dataframe Column Reference Bug (updated)
@seanmor5 Location: In Chapter 1, on page 14 Description: While attempting to cast the species column to a category in normalized_iris,...
/book-machine-learning-in-elixir#errata
0 80 1
New
daneroo
PragProg Customers

Machine Learning in Elixir: Code Repository
Machine Learning in Elixir: Code Repository Can we get a link to a GitHub repository with all erratas for the examples patched, Then we...
/book-machine-learning-in-elixir#suggestion
2 51 0
New
shaolang
PragProg Customers

Machine Learning in Elixir: B5 Page 105 Incorrect application of min_max_scale
@seanmor5 Test data should be scaled using the learned parameters from scaling train data. For example, if train data contains [1, 2, 3,...
/book-machine-learning-in-elixir#errata
0 21 1
New
hugobarauna
PragProg Customers

Machine Learning in Elixir: wrong GitHub repo URL (page 92)
@seanmor5 Instead of https://github.com/jonathanklosko/meow it’s https://github.com/jonatanklosko/meow
/book-machine-learning-in-elixir#errata
0 22 0
New
bosko
PragProg Customers

Machine Learning in Elixir P1.0: Chapter 10 (page 224) definition of batch function
@seanmor5 Definition of batch function in the Data module line |> Stream.chunk_every(batch_size, :discard) should be |> Stream....
/book-machine-learning-in-elixir#errata
0 24 0
New
CoderDennis
PragProg Customers

Machine Learning in Elixir: chapter 7 CNN model accuracy no better than MLP (page 160)
When training the cnn_model, I get the following output: Epoch: 0, Batch: 150, accuracy: 0.4985513 loss: 7.6424022 Epoch: 1, Batch: 163,...
/book-machine-learning-in-elixir
0 26 3
New

Most Active Last Three Years Top

PragmaticBookshelf
In The Spotlight

Spotlight: Sean Moriarity (Author) Interview and AMA!
Author Spotlight: Sean Moriarity @seanmor5 Machine learning sounds both magical and difficult, but with the right tools and the right...
#nx/book-machine-learning-in-elixir/elixir#author-spotlight#otp#beam#machine-learning
29 1991 13
New
martincabrera
PragProg Customers

Machine Learning in Elixir: Error in Chapter 1, first code snippet of "Preparing the Data for Training" (page 13)
@seanmor5 The mutate macro from the Explorer.DataFrame variable does not like variables: It works without the variable:
/book-machine-learning-in-elixir#errata
2 761 3
New
bdarla
PragProg Customers

Machine Learning in Elixir: error thrown in code snippet (page 44)
Running the code snippet of Chapter 2 on page 44 of version B1.0, I get the following error: Evaluation process terminated - an exceptio...
/book-machine-learning-in-elixir#errata
6 623 5
New
pieteeken
PragProg Customers

Machine Learning in elixir: Some problems with chapter 7 in Version B2.0
@seanmor5 Title: Machine Learning in elixir: Some problems with chapter 7 in Version B2.0 On 3 january 2024 I downloaded the Cats & ...
#errata#machine-learning-in-elixir/book-machine-learning-in-elixir
1 373 1
New
eeide
PragProg Customers

Machine Learning in Elixir: Chapter 1 Minor Nits (multiple pages)
Some minor nits in the beta version: “but is often considered it’s own type of machine learning.” → should be “its” “represents a d...
/book-machine-learning-in-elixir#errata#typo
1 444 1
New
jakesgordon
PragProg Customers

Machine Learning in Elixir - Wine datasets wont download (page 128)
@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...
/book-machine-learning-in-elixir#errata
4 592 3
New
justincjohnson
PragProg Customers

Machine Learning in Elixir: model accuracy
@seanmor5 In chapter 1, the accuracy of the model is 0.9666666. On my laptop I only get an accuracy of 0.5333333. Is that a problem? ...
/book-machine-learning-in-elixir#question
1 583 3
New
sdball
PragProg Customers

Machine Learning in Elixir: accuracy on the test data
Title: Machine Learning in Elixir: Chapter 1 Example: Flower classification - final accuracy on the test data is inconsistent. When com...
/book-machine-learning-in-elixir#question
3 535 4
New
polmiro
PragProg Customers

Machine Learning in Elixir: Error in Chapter 9, identifying cats and dogs again
@seanmor5 the code provided I am running into an error when training the first model that uses transfer learning with ONNX model mobilen...
/book-machine-learning-in-elixir#question
1 505 2
New
shawn_leong
PragProg Customers

Machine Learning in Elixir: Chapter 1, Poor Accuracy when following the code in book
Hey @seanmor5, I’m having great training accuracy but poor evaluation accuracy for the example in Chapter 1 when following the code in t...
/book-machine-learning-in-elixir#errata
2 514 1
New
haubie
PragProg Customers

Machine Learning in Elixir: Mutate not working, missing pin ^ (Iris example, Chapter 1)
@seanmor5 For Explorer.Query to access variables defined outside of the query ^ must be used. Updated in the example below: cols = ~w(...
/book-machine-learning-in-elixir#errata
3 502 1
New
egutter
PragProg Customers

Machine Learning in Elixir: Nx.random_uniform is deprecated (page 44)
Hi, When running tensor = Nx.random_uniform({1_000_000}) There’s a warning message warning: Nx.random_uniform/1 is deprecated. Use Nx....
/book-machine-learning-in-elixir#suggestion
0 498 0
New
adamt
PragProg Customers

Machine Learning in Elixir: Model output "iris_features" => nil, not tuple
@seanmor5 Title: Machine Learning in Elixir (epub so pages different i think) From book: Current output: Diff: inputs: %{"ir...
/book-machine-learning-in-elixir#errata
1 491 1
New
simple
PragProg Customers

Machine Learning in Elixir: Chapter 10/11 Code fixes that worked for me (Page 226-260)
Page 226 Mix install uses older versins of exla, should 0.6 to work with cuda120 Page 230 targets pipeline in Data module misses |>...
/book-machine-learning-in-elixir#errata
2 408 1
New
adamt
PragProg Customers

Machine Learning in Elixir: Explorer iris output is different from latest Explorer
@seanmor5 In book: Actual Diff-ish Polars[150 x 5]
/book-machine-learning-in-elixir#errata
0 460 1
New

Most Active Over Three Years Top

egutter
PragProg Customers

Machine Learning in Elixir: Missing option in confusion matrix (page 104)
Version: B1.0 On page 104 the code: Scholar.Metrics.confusion_matrix(test_targets, test_preds) throws an error: required :num_classes ...
/book-machine-learning-in-elixir#errata
0 467 2
New
pieteeken
PragProg Customers

Machine Learning in Elixir: Some remarks on chapter 8 version B2.0 and cuda
@seanmor5 Machine Learning in Elixir Some remarks on chapter 8 version B2.0 seanmor5 page 177 It is already mentioned here: :discar...
/book-machine-learning-in-elixir#cuda
0 447 1
New
shawn_leong
PragProg Customers

Machine Learning in Elixir: Nx.random_uniform/1 is deprecated. (B1.0, Chapter 6, Page 128)
Hey @seanmor5 , Similar to the errata on deprecation on page 44, on page 128: Nx.random_uniform({}) |> NeuralNetwork.predict(w1, b1,...
/book-machine-learning-in-elixir#errata
0 441 1
New
Chris660
PragProg Customers

Machine Learning in Elixir: query on normalising data between 0..1 (page 5)
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...
/book-machine-learning-in-elixir#errata
0 432 1
New
shawn_leong
PragProg Customers

Machine Learning in Elixir: Plot of given `profits` function does not match the expected plot (B1.0, Chapter 3, Page 65)
Hey @seanmor5, The function given in the book defn profits(trees) do trees |> Nx.pow(4) |> Nx.negate() |> Nx.add(Nx.mu...
/book-machine-learning-in-elixir#errata
1 394 1
New
sabiwara
PragProg Customers

Machine Learning in Elixir: Chapter 13 code errors
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...
/book-machine-learning-in-elixir#errata
3 339 7
New
yannvery
PragProg Customers

Machine Learning in Elixir: Using Clustering - Error on module name (page 100)
Version: B1.0 On page 100 (epub version) the code: model = Scholar.Clustering.KMeans.fit(train_inputs, ​num_clusters:​ 3) throws an er...
/book-machine-learning-in-elixir#errata
0 390 1
New
egutter
PragProg Customers

Machine Learning in Elixir: Missing model in Scholar prediction (page 103 & 104)
Version: B1.0 On page 103 & 104 where the code example is: Scholar.Linear.LogisticRegression.fit( train_inputs, train_targets, num_...
/book-machine-learning-in-elixir#errata
0 397 1
New
shawn_leong
PragProg Customers

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....
/book-machine-learning-in-elixir#errata
1 391 1
New
etnt
PragProg Customers

Machine Learning in Elixir: missing word on page 6?
Title: Machine Learning in Elixir: Learning to Learn with Nx and Axon (6) “You will sometimes see surprising due to precision issues.” ...
/book-machine-learning-in-elixir#errata
0 386 1
New
egutter
PragProg Customers

Machine Learning in Elixir: Minor error on tensors enumeration (page 98)
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: ...
/book-machine-learning-in-elixir#errata
0 385 1
New
froucoux
PragProg Customers

Machine Learning in Elixir B1.0: missing word? (p28)
“You will sometimes see surprising … due to precision issues.” Missing word, maybe “consequences” or “effects” ? Thanks for the great j...
/book-machine-learning-in-elixir#errata
0 384 1
New
bobek
PragProg Customers

Machine Learning in Elixir: inspect_expr/1 is deprecated (page 70)
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...
/book-machine-learning-in-elixir#errata
0 364 1
New
grossvogel
PragProg Customers

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...
/book-machine-learning-in-elixir#question
0 368 0
New
dompdv
PragProg Customers

Machine Learning in Elixir: typo in cross entropy formula
I guess the second log should be : 1-y_pred
/book-machine-learning-in-elixir#errata
0 351 1
New
Back to top

Book Info

Publisher: Pragmatic Bookshelf
Tag: #book-machine-learning-in-el...
Threads: 75
View on pragprog.com
View Main Thread
View Errata & Suggestions
Post Review
Create Journal
Post Errata
Post Suggestion
Post Question
Post General Discussion

Are you this book's author? To be notified of all posts made about it, sign up an account then click here, then select 'watching' from the bell icon in the top right corner.

Get money off!

The Pragmatic Bookshelf

35% off any eBook

Simply use coupon code "devtalk.com" at checkout. See full details here.

Latest

Machine Learning in Elixir: Chapter 4. Bug with avg_loss counting
PragProg Customers
Chapter 1: Dataframe Column Reference Bug (updated)
PragProg Customers
Machine Learning in Elixir P1.0: Chapter 10 (page 224) definition of batch function
PragProg Customers
Machine Learning in Elixir: Chapter 1 doesn't work with Axon 0.7 (page 26)
PragProg Customers
Machine Learning in Elixir: chapter 7 CNN model accuracy no better than MLP (page 160)
PragProg Customers
Machine Learning in Elixir: Code Repository
PragProg Customers
Machine Learning in Elixir: wrong GitHub repo URL (page 92)
PragProg Customers
Machine Learning in Elixir: B5 Page 105 Incorrect application of min_max_scale
PragProg Customers
Machine Learning in Elixir: Nx.Random.uniform_split wrong arguments 130
PragProg Customers
Machine Learning in Elixir: Error running last example in Chapter 1 (Evaluating the Trained Model)
PragProg Customers

View all Machine Learning in Elixir threads ❯

We ❤️ helpful members!

We reward our most helpful members via our MOTM scheme - by giving away a whopping 25 books per year!

Member of the Month

Devtalk Sponsors

Pragmatic Bookshelf

Practical resources that improve the lives of professional developers.

Erlang Solutions

We build trusted fault-tolerant systems that scale to billions of users.

AppSignal

Catch errors, track performance, monitor hosts and more.

WyeWorks

Enabling companies to succeed by building software people love.

Pragmatic Studio

Courses that'll move you from confusion to "Aha, now I get it!"

View all our sponsors ❯

Filter by Type:

More from PragProg

Related Portals

Devtalk Sponsors

Pragmatic Bookshelf

Practical resources that improve the lives of professional developers.

Erlang Solutions

We build trusted fault-tolerant systems that scale to billions of users.

AppSignal

Catch errors, track performance, monitor hosts and more.

WyeWorks

Enabling companies to succeed by building software people love.

Pragmatic Studio

Courses that'll move you from confusion to "Aha, now I get it!"

View all our sponsors ❯

We're in Beta

About us Mission Statement See our Roadmap