# nicodjimenez/lstm

Minimal, clean example of lstm neural network training in python, for learning purposes.

Repository: https://github.com/nicodjimenez/lstm
Canonical: https://ross.abutalabs.com/products/nicodjimenez-lstm
Language: Python
License Family: other
Last push: 2021-07-09T20:49:34+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4063, "days_push": 1881, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1900, forks 659 (observed 2026-08-28T04:05:51.558180+00:00)

## What it is
A minimal, clean LSTM neural network implementation written from scratch in Python for learning purposes. It demonstrates LSTM training with backpropagation on a simple sequence prediction task.

## Use cases
- understand how lstm networks work internally
- learn lstm backpropagation from scratch
- minimal lstm implementation example in python
- study sequence prediction with neural networks
- teaching recurrent neural network concepts
- starting point for building custom lstm variants

## When to choose
- you want readable source code explaining lstm internals
- you are learning deep learning fundamentals and want a from-scratch implementation
- you need a small educational codebase to modify and experiment with

## When to avoid
- you need a production-ready or efficient lstm implementation
- you want gpu acceleration or modern framework features
- you need maintained code with a license for commercial use

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: deep-learning, education, tutorials
- platform: python
- tags: lstm, from-scratch, educational, neural-networks, sequence-prediction

## Member repositories
- nicodjimenez/lstm (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:51.558180+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:12:04.007673+00:00, confidence not recorded.
  - readme: https://github.com/nicodjimenez/lstm (fetched 2026-08-28T04:05:51.558180+00:00, sha 1b8b16b7b622)
- Data as of 2026-08-30T08:39:29.467469+00:00.