Pytorch LSTM RNN for reinforcement learning to play Atari games from OpenAI Universe. We also use Google Deep Mind's Asynchronous Advantage Actor-Critic (A3C) Algorithm. This is much superior and efficient than DQN and obsoletes it. Can play on many games

A tour of different optimization algorithms in PyTorch.

Notes about LLaMA 2 model

A collection of various gradient descent algorithms implemented in Python from scratch

From linear regression towards neural networks...

The project aimed to implement Deep NN / RNN based solution in order to develop flexible methods that are able to adaptively fillin, backfill, and predict time-series using a large number of heterogeneous training datasets.

Modified XGBoost implementation from scratch with Numpy using Adam and RSMProp optimizers.

[Python] [arXiv/cs] Paper "An Overview of Gradient Descent Optimization Algorithms" by Sebastian Ruder

📈Implementing the ADAM optimizer from the ground up with PyTorch and comparing its performance on six 3-D objective functions (each progressively more difficult to optimize) against SGD, AdaGrad, and RMSProp.

A fast, interactive tool to visualize how different gradient descent algorithms (like vanilla gradient Descent, Momentum, RMSprop, Adam, etc.) navigate complex loss surfaces in real time.

Short description for quick search

SC-Adagrad, SC-RMSProp and RMSProp algorithms for training deep networks proposed in

A Siamese Neural Network is a class of neural network architectures that contain two or more identical subnetworks. ‘identical’ here means, they have the same configuration with the same parameters and weights.

Dropout vs. batch normalization: effect on accuracy, training and inference times - code for the paper

Hands on implementation of gradient descent based optimizers in raw python

Hopfield NN, Perceptron, MLP, Complex-valued MLP, SGD RMSProp, DRAW

Neural Networks and optimizers from scratch in NumPy, featuring newer optimizers such as DemonAdam or QHAdam.

A research project on enhancing gradient optimization methods

Object recognition AI using deep learning

Library which can be used to build feed forward NN, Convolutional Nets, Linear Regression, and Logistic Regression Models.

Python library for neural networks.

A Repository to Visualize the training of Linear Model by optimizers such as SGD, Adam, RMSProp, AdamW, ASMGrad etc

Fully connected neural network for digit classification using MNIST data

AI-Face-Mask-Detector

in this repository we intend to predict Google and Apple Stock Prices Using Long Short-Term Memory (LSTM) Model in Python. Long Short-Term Memory (LSTM) is one type of recurrent neural network which is used to learn order dependence in sequence prediction problems. Due to its capability of storing past information, LSTM is very useful in predicting stock prices.

"Simulations for the paper 'A Review Article On Gradient Descent Optimization Algorithms' by Sebastian Roeder"

Curso Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization. Segundo curso del programa especializado Deep Learning. Este repositorio contiene todos los ejercicios resueltos. https://www.coursera.org/learn/neural-networks-deep-learning

An OOP Deep Neural Network using a similar syntax as Keras with many hyper-parameters, optimizers and activation functions available.

Siamese Neural Network used for signature verification with three different datasets

Gradient_descent_Complete_In_Depth_for beginners