AmeyaJagtap/Adaptive_Activation_Functions
We proposed the simple adaptive activation functions deep neural networks. The proposed method is simple and easy to implement in any neural networks architecture.
This project helps researchers and engineers build more accurate and efficient deep neural networks, especially for solving complex scientific and engineering problems. You provide your problem, often involving partial differential equations or complex data, and it delivers a neural network that learns faster and provides more precise solutions than traditional methods. This is for anyone working with deep learning to model physical systems or analyze intricate datasets.
No commits in the last 6 months.
Use this if you are developing deep learning models for regression tasks or solving partial differential equations and need to improve your model's convergence speed and accuracy, particularly for forward problems.
Not ideal if you are primarily focused on classification tasks or if your current fixed-activation neural networks already meet your performance needs.
Stars
13
Forks
6
Language
—
License
MIT
Category
Last pushed
Feb 01, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AmeyaJagtap/Adaptive_Activation_Functions"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
digantamisra98/Mish
Official Repository for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]
Sentdex/nnfs_book
Sample code from the Neural Networks from Scratch book.
itdxer/neupy
NeuPy is a Tensorflow based python library for prototyping and building neural networks
vzhou842/cnn-from-scratch
A Convolutional Neural Network implemented from scratch (using only numpy) in Python.
nicklashansen/rnn_lstm_from_scratch
How to build RNNs and LSTMs from scratch with NumPy.