Several feedforward neural networks with different hidden layer sizes and activation functions learning the distribution of the Bessel Function of the First Kind with order 0.
-
Updated
Aug 27, 2026 - Python
#
activation-functions-analysis
Here are 10 public repositories matching this topic...
Activation Features Empowered: An Efficient Gradient-Free Proxy to Zero-Shot Neural Architecture Search
deep-neural-networks theoretical-computer-science neural-architecture-search zeroshot-learning performanceevaluation activation-functions-analysis
-
Updated
May 10, 2026 - Python
TensorFlow/Keras implementation of the trainable Sb-PiPLU activation function and the image-classification experiments associated with the IEEE Access paper.
deep-learning tensorflow keras medical-imaging image-classification svhn convolutional-neural-networks cifar10 parametric-activation activation-functions-analysis sb-piplu
-
Updated
Aug 1, 2026 - Python
Implementasi forward pass Multi-Layer Perceptron (MLP) 1 hidden layer dari nol menggunakan numpy murni (tanpa framework deep learning).
deep-learning numpy linear-algebra jupyter-notebook matrix-multiplication neural-networks from-scratch machine-learning-basics multilayer-perceptron tanh-activation universal-approximation-theorem mathematical-proof forward-pass activation-functions-analysis lstm-fundamentals
-
Updated
Aug 20, 2026 - Jupyter Notebook
Built a configurable neural network from scratch in Python using NumPy, implementing feedforward processing, backpropagation, multiple activation functions, momentum, data normalization, accuracy testing, and training-loss visualization with Matplotlib.
machine-learning deep-learning numpy python3 artificial-intelligence neural-networks matplotlib feedforward-neural-network momentum gradient-descent data-normalization backpropagation from-scratch softmax activation-functions-analysis
-
Updated
Sep 16, 2026 - Python
This project implements the classical LeNet-5 CNN for MNIST digit classification using PyTorch. It covers a complete pipeline from data preprocessing to deployment. The model achieves ~98.8% test accuracy, showing the strong effectiveness of early CNN architectures for image classification.
convolutional-neural-networks pooling-layers stochastic-gradient-descent model-deployment learning-rate-scheduling model-generalization pytorch-deep-learning confusion-matrix-analysis real-time-inference overfitting-analysis mnist-digit-classification end-to-end-ml-pipeline lenet5-cnn feature-extraction-cnn hierarchical-feature-learning activation-functions-analysis tanh-vs-relu batch-size-generalization cnn-regularization class-wise-performance
-
Updated
Apr 27, 2026 - Jupyter Notebook
Systematic study of the Information Bottleneck theory of deep learning; comparing Tanh vs ReLU, SGD vs BGD, and Binning vs KDE mutual information estimation across multiple CNN and feedforward architectures on MNIST.
python compression deep-learning kde information-theory cnn pytorch neural-networks mutual-information minst information-bottleneck activation-functions-analysis
-
Updated
Jul 10, 2026 - Jupyter Notebook
Ayah Lab is a Deep Learning based Quranic verse theme classification and exploration platform with Streamlit, PyTorch, and Transformer models.
nlp machine-learning deep-learning neural-network optimization cnn embeddings classification quran mlp bert-model streamlit-webapp bilstm-model activation-functions-analysis
-
Updated
May 25, 2026 - Jupyter Notebook
Repository dedicated to analysing and comparing the quality and fidelity of activation function families across wide array of metrics.
-
Updated
Aug 25, 2026 - Python
This folder contains the supporting code and data for arXiv:2607.03664
-
Updated
Aug 4, 2026 - Python
Add this topic to your repo
To associate your repository with the activation-functions-analysis topic, visit your repo's landing page and select "manage topics."