Gana016's Projects
online food delivery app
this model is based on stacked auto encoders where we will be building this model with 4 hidden layers which is using sigmoid activation and the loss is calculated by RMS, this model is a recomended system for movie reviews, this model predicts the review rating for the movies which user didnt saw (from 1-5) the model is trained with 100k reviews , but i am also providing the 1million reviews dataset for experimenting
this churn modelling prediction is based on artificial neural networks and this model is trained with the datasets corresponding to a bank database which contains the details of all the customers from past six months and after the model is trained it can predict whether the customer will leave the bank or not! in this model i have used two hidden layers, one output layer and one input layer,the activation functions are Relu for hidden layers and sigmoid function for output layers
in this project i have done data analyzing on the covid 19 datasets, i have shown the difference between matplotlib,pandas,plotly and plotly express and made different visualisations and also i showed on how to use folium in jupyter notebook. I made detailed description about different plottings in python (Data visualisation).
Ah shit, here we go again.
Software Engineering project for helping faculty to manage courses.
Students view for Digital-course-file-system
Here this is a simple python program where i have used opencv to detect face and eyes.
this model is based on self organizing maps, the model is trained with the list of customers in the bank who had applied for credit card and this dataset is trained on som model and a map is formed from that map you need to select which has the most MID(mean inter neuron distance) and concatenate the mappings and finally the result is obtained from mappings, the dataset is obtained from UCI machine learning library.
My portfolio
My Portfolio Website
Join the GitHub Graduation Yearbook and "walk the stage" on June 5.
in this model i have prepared a network of 4 lstm layers and i choosed adam optimiser and for each layer i had released a drop out of 20% and the model is trained from the dataset taken from google stock from 2012 to 2016 and the predicted using 2017 january dataset and in this model it cheacks with the last 60 days before prediction and the results are compared by ploting graph with the help of matplotlib.
MLH hackathon Submission.
The standard example for machine learning these days is the MNIST data set, a collection of 70,000 handwriting samples of the numbers 0-9. now we predict which number each handwritten image represents.Each image is 28x28 grayscale pixels, so we treat each image as just a 1D array, or tensor, of 784 numbers.MNIST provides 60,000 samples in a training data set, 10,000 samples in a test data set, and 5,000 samples in a "validation" data set. We haven't talked about validation sets before, but their intent is to be used for model selection. So you'd use validation data to select your model, train the model with the training set, and then evaluate the model using the test data set.The training data, after we "flatten" it to one dimension using the reshape function, is therefore a tensor of shape [60,000, 784] - 60,000 instances of 784 numbers that represent each image. we define our architecture by 1 hidden layer and we use relu for activating nodes and we use 20 epochs and keep batch size of 100.
this is a model which predicts whether the input image is cat or dog,this cnn model is trained with dataset of images of cats and dogs (8000 images), two convolution layers are used with activation functions of Relu(rectifier),sigmoid(for ouput layer).