Implementation of optimization algorithms for training extreme learning neural networks, including momentum (heavy ball) descent and smoothed gradient methods, implemented from scratch.
-
Updated
Apr 2, 2026 - Python
#
sgd
Here are 86 public repositories matching this topic...
A Python project implementing a neural network framework from scratch using NumPy. Includes fully connected (Dense) layers, ReLU and Sigmoid activations, a simple SGD optimizer, and a minimal training loop. Designed for hands-on learning of neural network fundamentals without relying on any deep learning frameworks
python machine-learning neural-network numpy sgd mini-framework deep-learning-from-scratch activation-function
-
Updated
Apr 1, 2026 - Python
JAX compilation of RDDL description files, and a differentiable planner in JAX.
control reinforcement-learning controller automatic-differentiation planning sgd policy-gradient model-based-control nonlinear-dynamics backpropagation nonlinear-optimization stochastic-gradient-descent planning-domain-definition-language planning-algorithms nonlinear-control sgd-optimizer jax rddl differentiable-simulations gradient-based-optimisation
-
Updated
Mar 31, 2026 - Python
Research project analyzing stability and robustness of deep learning optimizers (SGD, Adam, SAM) under label noise and precision constraints.
machine-learning deep-learning optimization pytorch mnist sgd research-project adam numerical-stability label-noise float32 float64 model-robustness sam-optimizer
-
Updated
Mar 29, 2026 - Python
Visual and interactive guide to optimization algorithms — from gradient descent to Adam, with Python notebooks and animations
visualization python education machine-learning deep-learning optimization mathematics sgd gradient-descent numerical-optimization adam
-
Updated
Mar 25, 2026 - Python
Empirical comparison of SGD, Adam, RMSprop, Adagrad and L-BFGS on CIFAR-10 convergence analysis, gradient norm tracking, and loss landscape visualisation
deep-learning optimization pytorch sgd adam distributed-optimization cifar-10 convergence-analysis loss-landscape
-
Updated
Mar 12, 2026 - Python
A from-scratch implementation of feedforward neural networks using NumPy. Developed for the Artificial Intelligence Fundamentals course at the University of Parma, featuring manual backpropagation, mini-batch SGD, and inverted dropout on the MNIST dataset.
machine-learning neural-network numpy data-visualization python3 artificial-intelligence mnist sgd gradient-descent academic-project backpropagation deep-learning-from-scratch
-
Updated
Feb 23, 2026 - Python
Optimizer Comparison Study - Empirical analysis of SGD vs Adam performance on MNIST with various initialization and scheduler configurations
-
Updated
Feb 8, 2026 - Python
A pure NumPy implementation of Ridge Regression (L2 Regularization) from scratch. Features vectorized Minibatch Stochastic Gradient Descent (SGD) and manual hyperparameter grid search without using scikit-learn.
data-science machine-learning optimization numpy linear-regression pandas sgd gradient-descent ridge-regression python-from-scratch
-
Updated
Feb 6, 2026 - Python
Implementing PyTorch Optimizers from Scratch
-
Updated
Nov 12, 2025 - Python
EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classification
machine-learning statistics deep-learning neural-network pytorch sgd classification ensemble-learning openml cifar10 loss-functions icml pcam empirical-risk-minimization overfitting-reduced combing surrogate-loss overfitting-prevention icml-2025
-
Updated
Nov 1, 2025 - Python
Saccharomyces Genome Database (SGD) REST API wrapper
-
Updated
Jan 31, 2026 - Python
Exercises of the Laboratory of Computational Physics Mod. B
machine-learning deep-learning tensorflow keras sgd xgboost regularization convolutional-neural-networks t-sne dbscan optimization-algorithms
-
Updated
Apr 22, 2025 - Python
minimum bipartite matching via Riemann optimization
-
Updated
Jan 6, 2025 - Python
This work was published at IEEE ISIT 2022, where we proposed a novel algorithm named G-CADA aiming to improve the time and communication efficiency of distributed learning systems based on grouping and adaptive selection methods 😄
-
Updated
Dec 19, 2024 - Python
My beautiful Neural Network made from scratch and love. It plays the game Flappy-Birds flawlessly, in 3 to 9 generations!!
machine-learning ai genetic-algorithm neuroevolution sgd neural-networks perceptron gradient-descent xor flappy-bird-game xavier-initializer activation-functions sigmoid-activation
-
Updated
Aug 31, 2024 - Python
A repo that contains source code for my blog "Deep Learning Optimizers: A Comprehensive Guide for Beginners (2024)"
-
Updated
Jul 26, 2024 - Python
Parametric estimation of multivariate Hawkes processes with general kernels.
-
Updated
May 27, 2024 - Python
Amortized version of the differentially private SGD algorithm published in "Deep Learning with Differential Privacy" by Abadi et al. Enforces privacy by clipping and sanitising the gradients with Gaussian noise during training.
python privacy research deep-learning tensorflow mnist sgd gradient-descent differential-privacy tensorflow2
-
Updated
Apr 12, 2024 - Python
Improve this page
Add a description, image, and links to the sgd topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the sgd topic, visit your repo's landing page and select "manage topics."