WikuAgil

WikuAgil's Stars

• KhamisiKibet/QT-PyQt-PySide-Custom-Widgets

  Awesome custom widgets made for QT Desktop Applications. Simplify your UI development process. These widgets can be used in QT Designer then imported to PySide code.

  Language:Python80917105234

• Wanderson-Magalhaes/Splash_Screen_Python_PySide2

  Language:Python1534363

• ingwant/PyQt5-Video-Book

  Language:Python1503182

• mdminhazulhaque/pyqt-bpnn

  :parking: Back-Propagation Neural Networks example using PyQt GUI

  Language:Python30205

• codefirstio/pyqt5-full-app-tutorial-for-beginners

  Source code for a tutorial series for building a fully functional app with PyQt5. Playlist: https://www.youtube.com/playlist?list=PLs3IFJPw3G9LTcNjRVR6BSJwUaoj44rCV

  Language:Python291020

• akshaybaj/ML_GUI

  This repo contains the code for a GUI which can be used for training different ML models as well as for data visualisation

  Language:Python20317

• zherbz/EncoderDecoder

  Hybrid CNN-LSTM Encoder Decoder algorithm for multi-step reservoir storage volume forecasting

  Language:Python17305

• RezaSaadatyar/Time-Series-Analysis-in-Python

  This repository contains Python functions for predicting time series.

  Language:Python13300

• aysebilgegunduz/FeedFwBackProp

  Simple multi layer perceptron application using feed forward back propagation algorithm

  Language:Python7202

• blackepars/feature_extraction_gui

  7204

• OmkarThawakar/BackProp-With-Momentum

  Implementation of Error BackPropagation Training Algorithm With Momentum

  Language:Jupyter Notebook610

• irania9O/Restaurant

  This is a multiple restaurant management project built graphical interface with the pyqt5 library.

  Language:Python5100

• oekosheri/Flexible-time-series-forecasting

  flexible time series forecasting using machine learning

  Language:Python5202

• amansingh1701/Backpropagation-Algorithm-for-training-a-neural-network-using-MNIST-Dataset

  The goal of this project is to label images of 10 handwritten digits of “zero”, “one”,...,“nine”. The images are 28 by 28 in size (MNIST dataset), which we will be represented as a vector x of dimension 784 by listing all the pixel values in raster scan order. The labels are 0,1,2,...,9 corresponding to 10 classes as written in the image. There are 3000 training cases, containing 300 examples of each of 10 classes. PROBLEM 1: Here you must read an input file. Each line contains 785 numbers (comma delimited): the first values are between 0.0 and 1.0 correspond to the 784 pixel values (black and white images), and the last number denotes the class label: 0 corresponds to digit 0, 1 corresponds to digit 1, etc. PROBLEM 2: Implement the backpropagation algorithm in a zero hidden layer neural network (weights between input and output nodes). The output layer should be a softmax output over 10 classes corresponding to 10 classes of handwritten digits (e.g. an architecture: 784 > 10). Your backprop code should minimize the cross-entropy entropy function for multi-class classification problem (categorical cross entropy). PROBLEM 3: Extend your code from problem 2 to support a single layer neural network with N hidden units (e.g. an architecture: 784 > 10 > 10). These hidden units should be using sigmoid activations. PROBLEM 4: Extend your code from problem 3 (use cross entropy error) and implement a 2-layer neural network, starting with a simple architecture containing N hidden units in each layer (e.g. with architecture: 784 > 10 > 10 > 10). These hidden units should be using sigmoid activations. Extend your code from problem 4 to implement different activations functions which will be passed as a parameter. In this problem all activations (except the final layer which should remain a softmax) must be changed to the passed activation function. PROBLEM 6: Extend your code from problem 5 to implement momentum with your gradient descent. The momentum value will be passed as a parameter. Your function should perform “epoch” number of epochs and return the resulting weights.

  Language:Jupyter Notebook4

• karlduggan/LittleBlackBookApp

  "Little Black Book" is CRUD application built with PyQt5, Sqlite and python.

  Language:Python4003

• SamaMedhat1/MLP-using-Backpropagation

  Python GUI app contains an implemantion for Back-Propagation learning algorithm on a multi-layer neural networks, which can be able to classify a stream of input data to one of a set of predefined classes.

  Language:Python3

• Shashwat4K/Implementing-Back-Propagation

  Developing BackPropagation algorithm simulation from scratch.

  Language:Python3200

• abdelhafidAy36/Calculator-and-CRUD-Disktop-Applications-using-PyQt5-library

  Language:Python2

• aoso3/Neural-Networks-Implementation

  Implementation of some Neural Networks algorithms like (Backpropagation, Backpropagation with momentum, Leverage and Simulated annealing)

  Language:C#2200

• freddywicaksono/python_pyqt5_crud

  Create CRUD application using python and pyqt5 but not OOP with mysql database

  Language:Python2

• LucasAlegre/backpropagation

  Implementation of a fully connected neural network from scratch using numpy.

  Language:Python2200

• AlexanderMath/npnet

  Neural Network implemented in Numpy with backpropagation and momentum.

  Language:Python1200

• bersilin-robert1609/CS6910-Assignment1

  This repository contains the files for the first assignment of the course CS6910 - Deep Learning at IIT Madras.

  Language:Python1100

• caioissa/temporal-stock-prediction-slidingwindow

  Deep learning and sliding windowing for temporal series of US Stockmarket data

  Language:Python1

• chanbin/Machine_Running

  Sigmoid, Softmax, Backpropagation, ReLU, Dropout, momentum

  Language:Python1000

• greenDev7/DigitRecognitionCanvas

  Created with CodeSandbox

  Language:Vue1100

• mafr017/BNN_GPA

  Predicting GPA Using Backpropagation

  Language:Python1101

• michtom/MLP-from-scratch

  An implementation of MLP Neural Network using plain numpy, with backpropagation, momentum, RMSProp and different activtion functions.

  Language:Jupyter Notebook1

• Samuel-Bachorik/machine_learning_library

  Automatic backpropagation implemented in numpy,

  Language:Python1300

• shythm/uos-simple-mlp

  Simple Multi-Layer Perceptron(MLP) with forward and backward propagation

  Language:Python1100