Phoenix8215/build_neural_network_from_scratch_CPP
Created a simple neural network using C++17 standard and the Eigen library that supports both forward and backward propagation.
This C++ program helps deep learning beginners understand how a basic neural network processes data. It takes in grayscale images of handwritten digits, like those from the MNIST dataset, and outputs predictions about which digit is shown. This tool is ideal for students or educators who want to manually inspect the core mechanics of neural networks, specifically forward and backward propagation.
No commits in the last 6 months.
Use this if you are learning or teaching the foundational principles of neural networks and want to see a simplified, working implementation.
Not ideal if you need a production-ready neural network, a network with more complex architectures or activation functions, or if you prefer using high-level machine learning frameworks.
Stars
10
Forks
1
Language
C++
License
—
Category
Last pushed
Jul 27, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Phoenix8215/build_neural_network_from_scratch_CPP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Dobiasd/frugally-deep
A lightweight header-only library for using Keras (TensorFlow) models in C++.
flashlight/flashlight
A C++ standalone library for machine learning
wichtounet/dll
Fast Deep Learning Library (DLL) for C++ (ANNs, CNNs, RBMs, DBNs...)
NVlabs/tiny-cuda-nn
Lightning fast C++/CUDA neural network framework
KasperskyLab/knp
Kaspersky Neuromorphic Platform