# curiousily/Deep-Learning-For-Hackers

Machine Learning tutorials with TensorFlow 2 and Keras in Python (Jupyter notebooks included) - (LSTMs, Hyperameter tuning, Data preprocessing, Bias-variance tradeoff, Anomaly Detection, Autoencoders, Time Series Forecasting, Object Detection, Sentiment Analysis, Intent Recognition with BERT)

Repository: https://github.com/curiousily/Deep-Learning-For-Hackers
Canonical: https://ross.abutalabs.com/products/deep-learning-for-hackers
Homepage: https://mlexpert.io
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: deep-learning, tensorflow, machine-learning, artificial-intelligence, python, keras, neural-networks, jupyter-notebooks, tensorflow-tutorial, lstms, autoencoders, object-detection, image-augmentation, time-series-forecasting, time-series-classification, anomaly-detection, sentiment-analysis, intent-recognition, bert
Last push: 2020-04-23T06:08:54+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2688, "days_push": 2323, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1073, forks 433 (observed 2026-08-28T04:03:28.919936+00:00)

## What it is
A free online book and collection of Jupyter notebook tutorials teaching deep learning fundamentals with TensorFlow 2 and Keras. It covers practical topics across computer vision, NLP, and time series analysis, including LSTMs, autoencoders, anomaly detection, object detection, and BERT-based intent recognition.

## Use cases
- learn deep learning with tensorflow 2 and keras
- time series forecasting with lstms tutorial
- anomaly detection in time series using autoencoders
- sentiment analysis and intent recognition with bert
- how to fix overfitting and underfitting models
- hyperparameter tuning guide for neural networks
- object detection tutorial with tensorflow
- handling imbalanced datasets in machine learning

## When to choose
- you want free, hands-on Jupyter notebook tutorials for TensorFlow 2 and Keras
- you are learning practical ML across vision, NLP, and time series
- you prefer runnable notebooks you can open directly in Colab

## When to avoid
- you need up-to-date coverage of the latest TensorFlow or Keras APIs, as the material dates from 2020
- you need production-grade code or long-term support
- you are looking for PyTorch-based tutorials

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, nlp, data-science
- domain: deep-learning, machine-learning, tutorials, computer-vision
- platform: python, cross-platform
- tags: tensorflow, keras, jupyter-notebooks, lstm, autoencoders, time-series-forecasting, anomaly-detection, object-detection, sentiment-analysis, bert, hyperparameter-tuning, natural-language-processing

## Member repositories
- curiousily/Deep-Learning-For-Hackers (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:28.919936+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 2026-08-30T06:53:36.268783+00:00, confidence not recorded.
  - readme: https://github.com/curiousily/Deep-Learning-For-Hackers (fetched 2026-08-28T04:03:28.919936+00:00, sha 7e33007eeaea)
  - homepage: https://mlexpert.io (fetched 2026-08-29T12:55:39.745483+00:00, sha 36849e3fc4f4)
  - site_page: https://www.mlexpert.io/academy/v1/setup-and-toolkit/local-ai-quickstart (fetched 2026-08-29T12:55:39.757222+00:00, sha 2b295caeb746)
  - site_page: https://www.mlexpert.io/academy/v1/setup-and-toolkit/langchain-quickstart (fetched 2026-08-29T12:55:39.759744+00:00, sha e7bd62e18b03)
  - site_page: https://www.mlexpert.io/changelog (fetched 2026-08-29T12:55:39.755077+00:00, sha 69be5f79923d)
- Data as of 2026-08-30T08:39:29.467469+00:00.