tftensor is a tensor library implemented in Rust. It offers tensor operations, automatic differentiation, and supports basic neural network training functionalities.
-
Updated
Aug 26, 2024 - Rust
#
nn-from-scratch
Here are 6 public repositories matching this topic...
A collection of notebooks from my applied AI minor, featuring projects in machine learning, deep learning, and a neural network built from scratch.
-
Updated
Jun 20, 2024 - Jupyter Notebook
A scratch-built NumPy implementation of a Fully Connected Neural Network, with a sequential model API, a variety of layers (Linear, ReLU, BatchNorm), loss functions (MSE, SoftmaxCrossEntropy), and a robust training `Solver` to create and train multi-layer perceptrons for both classification and regression.
python deep-learning numpy university-project batch-normalization neural-networks course-project backpropagation fully-connected-neural-network nn-from-scratch
-
Updated
Nov 1, 2025 - Python
A simple NumPy-based deep learning framework. Create and train neural networks easily, experiment with backpropagation, optimization, and explore the code to grasp the inner workings.
framework deep-neural-networks deep-learning tensorflow pytorch neural-networks deep-learning-library deep-learning-framework dnn-from-scratch nn-from-scratch
-
Updated
May 12, 2023 - Python
A microscope for informed training of multi-layer perceptron, diagnosing training issues at granular level and accelerating learning and rapid prototyping.
-
Updated
Oct 27, 2025 - Python
Mini-library that implements a simple version of a feedforward neural network (FNN) and convolutional neural network (CNN) from scratch using Python and PyTorch
-
Updated
Nov 15, 2024 - Jupyter Notebook
Improve this page
Add a description, image, and links to the nn-from-scratch topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the nn-from-scratch topic, visit your repo's landing page and select "manage topics."