gitwtfhub

wtf is boltzmann?

whilo/boltzmann — explained in plain English

Analysis updated 2026-07-17 · repo last pushed 2015-10-01

★ 67ClojureAudience · researcherComplexity · 4/5DormantSetup · moderate

TL;DR

A Clojure deep learning library implementing Boltzmann Machines and related neural networks, with both a readable reference version and an optimized fast version of each algorithm.

Mindmap

mindmap
  root((boltzmann))
    What it does
      Restricted Boltzmann Machines
      Deep Belief Networks
      Unsupervised pattern learning
    Tech stack
      Clojure
      JVM
      core.matrix
    Use cases
      Learn deep learning algorithms
      Recognize handwritten digits
      Build pattern recognition systems
    Audience
      Data scientists
      ML students
      Clojure developers
    Design
      Readable version
      Optimized version
      MNIST benchmark example

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Why would anyone build with this?

REASON 1

Learn how Restricted Boltzmann Machines work by reading the clean, readable reference implementation.

REASON 2

Train a Deep Belief Network on the MNIST dataset to recognize handwritten digits.

REASON 3

Fine-tune an unsupervised-trained model with backpropagation using labeled data.

REASON 4

Use the optimized high-performance version to process larger real-world datasets.

What's in the stack?

Clojurecore.matrix

How it stacks up

whilo/boltzmannavelino/chrondbyogthos/flatiron
Stars679727
LanguageClojureClojureClojure
Last pushed2015-10-01——
MaintenanceDormant——
Setup difficultymoderatemoderatemoderate
Complexity4/54/53/5
Audienceresearcherdeveloperdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you spin it up?

Difficulty · moderate Time to first run · 1h+

Requires familiarity with Clojure and the JVM toolchain to run and modify.

Yoink these prompts

Prompt 1
Show me how to train a Restricted Boltzmann Machine on the MNIST dataset using this Clojure library.
Prompt 2
Explain the difference between boltzmann's readable and optimized implementations of the same algorithm.
Prompt 3
How do I use core.matrix in this library to understand the math behind Deep Boltzmann Machines?
Prompt 4
Write Clojure code using this library to fine-tune a pretrained Deep Belief Network with backpropagation.

Frequently asked questions

wtf is boltzmann?

A Clojure deep learning library implementing Boltzmann Machines and related neural networks, with both a readable reference version and an optimized fast version of each algorithm.

What language is boltzmann written in?

Mainly Clojure. The stack also includes Clojure, core.matrix.

Is boltzmann actively maintained?

Dormant — no commits in 2+ years (last push 2015-10-01).

How hard is boltzmann to set up?

Setup difficulty is rated moderate, with roughly 1h+ to a first successful run.

Who is boltzmann for?

Mainly researcher.

View the repo → Decode another repo

This repo across BitVibe Labs

Don't trust strangers blindly. Verify against the repo.

Other repos in this lane