rmsprop

Star

Here are 108 public repositories matching this topic...

Language:All

Filter by language

All108 Jupyter Notebook56 Python41 C#3 Java2 MATLAB2 C++1 HTML1 Swift1 TeX1

Sort:Most stars

Sort options

Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated

Nasdin /ReinforcementLearning-AtariGame

Star182

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

python reinforcement-learning deep-reinforcement-learning openai-gym pytorch lstm reinforcement-learning-algorithms a3c universe adam rmsprop actor-critic asynchronous-advantage-actor-critic reinforcement-agents a3c-lstm

UpdatedSep 19, 2024
Python

bentrevett /a-tour-of-pytorch-optimizers

Star94

A tour of different optimization algorithms in PyTorch.

optimization pytorch adadelta sgd optimization-algorithms adam adagrad rmsprop pytorch-optimizers

UpdatedDec 11, 2021
Jupyter Notebook

hkproj /pytorch-llama-notes

Star54

Notes about LLaMA 2 model

study-notes rmsprop attention-is-all-you-need kv-cache rotary-position-encoding llama2

UpdatedAug 30, 2023
Python

Arko98 /Gradient-Descent-Algorithms

Star35

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

machine-learning ai deep-learning machine-learning-algorithms ml deep-learning-algorithms gradient-descent adagrad rmsprop gradient-descent-algorithm adam-optimizer nesterov-accelerated-sgd nesterov-momentum nesterov momentum-optimization-algorithm

UpdatedFeb 28, 2023
Python

yaricom /TimeSeriesLearning

Star26

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.

deep-neural-networks deep-learning time-series recurrent-neural-networks pca-analysis rnn adagrad rmsprop leaky-relu adam-optimizer random-forest-regressor adamax

UpdatedAug 16, 2016
Python

RudreshVeerkhare /CustomXGBoost

Star26

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

numpy gradient-boosting-machine rmsprop adam-optimizer xgboost-algorithm implementation-of-algorithms

UpdatedJul 24, 2020
Jupyter Notebook

aromanro /MachineLearning

Star24

From linear regression towards neural networks...

data-science machine-learning neural-network linear-regression machine-learning-algorithms data-analysis logistic-regression gradient-descent backpropagation adagrad rmsprop generalized-linear-models multilayer-perceptron-network adam-optimizer nesterov-accelerated-sgd nesterov-momentum nadam

UpdatedSep 21, 2024
C++

harshraj11584 /Paper-Implementation-Overview-Gradient-Descent-Optimization-Sebastian-Ruder

Star24

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

adadelta momentum gradient-descent optimization-methods optimization-algorithms adam adagrad rmsprop gradient-descent-algorithm stochastic-optimizers stochastic-gradient-descent gradient-boosting adam-optimizer adamax stochastic-optimization batch-gradient-descent nesterov-accelerated-sgd amsgrad nesterov-momentum nadam

UpdatedMar 23, 2019
Python

thetechdude124 /Adam-Optimization-From-Scratch

Star17

📈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.

deep-learning artificial-intelligence optimization-algorithms rmsprop adam-optimizer sgd-optimizer

UpdatedJul 2, 2022
Jupyter Notebook

SSQ /Coursera-Ng-Improving-Deep-Neural-Networks-Hyperparameter-tuning-Regularization-and-Optimization

Star17

Short description for quick search

tensorflow dropout batch-normalization momentum softmax-regression l2-regularization rmsprop adam-optimizer mini-batch-gradient-descent bias-correction initialization gradient-check exponentially-weighted-averages learning-rate-decay

UpdatedJan 31, 2019
Python

mmahesh /variants-of-rmsprop-and-adagrad

Star14

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

python deep-neural-networks deep-learning optimization keras online-learning adagrad rmsprop stochastic-gradient-descent

UpdatedOct 5, 2018
Python

Chirag-Shilwant /One-Shot-Classification-using-Siamese-Network-on-MNIST-Dataset

Star10

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.

keras mnist-dataset one-shot-learning loss-functions rmsprop adam-optimizer siamese-network