https://github.com/christianromney/mnist-keras
A playground for studying machine learning
https://github.com/christianromney/mnist-keras
Last synced: 4 months ago
JSON representation
A playground for studying machine learning
- Host: GitHub
- URL: https://github.com/christianromney/mnist-keras
- Owner: christianromney
- Created: 2024-08-02T15:19:07.000Z (almost 2 years ago)
- Default Branch: master
- Last Pushed: 2024-08-02T15:22:52.000Z (almost 2 years ago)
- Last Synced: 2024-08-02T17:14:46.240Z (almost 2 years ago)
- Language: Python
- Size: 178 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.org
Awesome Lists containing this project
README
#+TITLE: mnist-keras Project
* Overview
This project is a playground for studying machine learning techniques. It
contains the "hello, world" of machine learning programs: [[https://en.wikipedia.org/wiki/MNIST_database#:~:text=The%20MNIST%20database%20(Modified%20National,training%20various%20image%20processing%20systems.][MNIST]] handwritten
image classification. High-level frameworks like Keras make it easy to build a
model with 97% accuracy in under a hundred lines of code.
** Learning Goals
- [X] Understand [[https://youtu.be/VMj-3S1tku0?si=DP_3O9cJaTAkWWzN][neural networks]] at a [[https://youtu.be/aircAruvnKk?si=3B7fAkIg_L13WQvo][high-level]]
- [X] Neurons modeled as a mathematical / functional graph
- [X] Representation as [[https://www.khanacademy.org/math/linear-algebra/vectors-and-spaces/linear-combinations/v/linear-combinations-and-span][linear combinations]] and basic [[https://youtu.be/fNk_zzaMoSs?si=RyxJYfhLcry4wyww][linear algebra]]
- [X] Weights, biases, activation functions
- [X] [[https://youtu.be/Ilg3gGewQ5U?si=ECiAVCVOcOvG_ZUw][Back-propagation]], [[https://youtu.be/tIeHLnjs5U8?si=oYLibvjf4u0W7gqr][differentiation]], [[https://youtu.be/AXqhWeUEtQU?si=wFsFBSyuqFAewbd5][partial]] [[https://youtu.be/ly4S0oi3Yz8?si=ARonsRGt2M-QT_MP][derivatives]], [[https://youtu.be/IHZwWFHWa-w?si=27mzINUeHkHVHMAz][gradient descent]]
- [X] Hyperparameters, regularization
- [ ] Kinds of Networks and their applications
- [ ] Deep Networks, GANs, RNNs, CNNs, Transformers, GPTs
- [ ] Tuning and Visualization Tools
- [ ] Data
- [ ] Arrays, Tensors
- [ ] Training, Validation, Test Data
- [ ] Manipulation and Cleaning
- [ ] Statistics and Feature Selection
- [-] Tools and Libraries
- [-] Python
- [X] [[https://keras.io/][Keras]]
- [X] [[https://pytorch.org/][Pytorch]]
- [ ] [[https://www.tensorflow.org/][Tensorflow]]
- [ ] [[https://jax.readthedocs.io/en/latest/quickstart.html][JAX]]
- [X] [[https://numpy.org/doc/stable/user/basics.html][Numpy]]
- [ ] [[https://pandas.pydata.org/docs/user_guide/10min.html][Pandas]]
- [ ] Scipy
- [ ] sklearn
- [ ] [[https://matplotlib.org/][Matplotlib]]
- [ ] Clojure
- [ ] [[https://neanderthal.uncomplicate.org/][Neanderthal]]
- [ ] Metamorph
- [ ] [[https://github.com/scicloj][Scicloj]]
- [ ] tech.ml.dataset / [[https://github.com/scicloj/tablecloth][Tablecloth]]
** More Resources
- Calculus
- [[https://calculusmadeeasy.org/][Made Easy]]
- [[https://calculusmadeeasy.org/16.html][Partial Differentiation]]
- [[https://ocw.mit.edu/ans7870/resources/Strang/Edited/Calculus/Calculus.pdf][Book (Strang)]]
- [[https://www.wolfram.com/wolfram-u/courses/mathematics/introduction-to-calculus/][Wolfram]]
- Linear Algebra
- [[https://aiprobook.com/numerical-linear-algebra-for-programmers/][Clojure Book]]
- Deep Learning
- [[https://www.deeplearningbook.org/][MIT Book]]
- [[https://aiprobook.com/deep-learning-for-programmers/][Clojure Book]]
- [[https://youtu.be/SmZmBKc7Lrs?si=d-DnSbmRnzJ0PgHN][Backpropagation]]