There are 3 repositories under autoencoder-neural-network topic.
Scripts and notebooks to accompany the book Data-Driven Methods for Dynamic Systems
Detecting malicious URLs using an autoencoder neural network
Training Deep AutoEncoders for Collaborative Filtering
Geometric Dynamic Variational Autoencoders (GD-VAEs) for learning embedding maps for nonlinear dynamics into general latent spaces. This includes methods for standard latent spaces or manifold latent spaces with specified geometry and topology. The manifold latent spaces can be based on analytic expressions or general point cloud representations.
Using convolutional autoencoders to remove random noise from seismic data.
Use auto encoder feature extraction to facilitate classification model prediction accuracy using gradient boosting models
Code to train a custom time-domain autoencoder to dereverb audio
All course material and codes of Generative Adversarial Networks Specialization offered by DeepLearning.ai
Autoencoder for Feature Extraction
Image enhancement using GAN's and autoencoders
Anomaly detection (also known as outlier analysis) is a data mining step that detects data points, events, and/or observations that differ from the expected behavior of a dataset. A typical data might reveal significant situations, such as a technical fault, or prospective possibilities, such as a shift in consumer behavior.
Gaussian Latent Dirichlet Allocation
Bias field correction for T-1 weighted MRI images for tumor detection
Autoencoder-based Feature Selection for the SN_DREAMS diabetic retinopathy dataset. (With Prof. S. Raman)
A gentle introduction to autoencoders with examples
This is my academic thesis work (individual). Submitted in partial fulfilment of the requirements for Degree of Bachelor of Science in Computer Science & Engineering
Columbia University Data Science Master Capstone Project. The goal of this project was to cluster trajectories by shape for later optimization.
An automatic adjustment model is developed for brightness adjustment in images.
Autoencoder is a type of neural network where the output layer has the same dimensionality as the input layer. In simpler words, the number of output units in the output layer is equal to the number of input units in the input layer. An autoencoder replicates the data from the input to the output in an unsupervised manner and is therefore sometimes referred to as a replicator neural network. The autoencoders reconstruct each dimension of the input by passing it through the network. It may seem trivial to use a neural network for the purpose of replicating the input, but during the replication process, the size of the input is reduced into its smaller representation. The middle layers of the neural network have a fewer number of units as compared to that of input or output layers. Therefore, the middle layers hold the reduced representation of the input. The output is reconstructed from this reduced representation of the input.
This project detect anomalous event in CCTV footage. For the training purposes only normal events are used. When any violence or anomalous event happen the model can detect it.
This project is used to detect a credit card fraud detection in an unsupervised manner. An autoencoder- based. an autoencoder with two hidden layer clustering model is build. an autoencoder with two hidden layer and K-means clustering unsupervised machine learning algorithm is used. The data has been taken from Kaggle
In this repo, a clean and efficient implementation of Fully-Connected or Dense Autoencoder is provided. The code alongside the video content are created for Machine Learning course instructed at Khajeh Nasir Toosi University of Technology (KNTU).
My implementation of autoencoders
Recommender System in python using autoencoders as part of Data Mining project
This research project intent is to review and demonstrate a comparability among recent auto-encoder methods by utilizing single architecture and resolution. Each method will be ranked based on selective performance measure in modeling healthy brain and the sensitivity towards domain shift.
Comparison of multiple methods for calculating MNIST hand-written digits similarity.
Filtering out the noise presented in the image by auto-enconder algorithm in TensorFow and Keras. Rare images, unclean crime images,medical noise images can be denoised and find out the desired outcome by using auto-encoders.
Text Digit Character Computer Vision using convolutional autoencoder
DATA: 606 | Capstone Project
Natural Disaster Analysis Website using Deep Learning & Poisson Distribution
Application of Machine Learning tools from Python
Colorizes grayscale images using a loaded model and displays original and predicted colorized versions.
Python autoencoder to remove blur from images