Radrangi

.github-workflows

a-2017

Public Repository for cs109a, 2017 edition

Agile_Data_Code_2

Code for Agile Data Science 2.0, O'Reilly 2017, Second Edition

AI-Notebooks

aiven-examples

Aiven "getting started" code examples

amazon-sagemaker-examples

Example notebooks that show how to apply machine learning and deep learning in Amazon SageMaker

analytics-integration-samples

Repository contains samples to integrate Watson IoT with different analytics services

anomaly-detection

Anomaly Detection model uses Spark for training and Spark Streaming for testing

anomaly_detection

reinforcement-learning

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

Radrangi/analytics-integration-samples

Repository contains samples to integrate Watson IoT with different analytics services

Radrangi/anomaly-detection

Anomaly Detection model uses Spark for training and Spark Streaming for testing

Radrangi/anomaly_detection

Radrangi/cellular_automata

we have a matrix with N columns and M rows. Each entry in the matrix is either 0 or 1. We always initialize Row 1. Given a rule , we construct the subsequent row by applying the rule to the previous row and so on. We can extend the number of rows indefinitely. Guided by one of the rules of cellular automata described : http://www.wolframscience.com/nksonline/page-53 Also added the feature to locate all occurances of a specific pattern. The pattern is based on 6 matrix elements located in two subsequent rows. This kind of analysis finds application in pattern recognition (growth of crystals in snowflakes, development of patterns in sea shells, improving unclear images, tracing mutaion)

Radrangi/cheatsheets-ai

Essential Cheat Sheets for deep learning and machine learning researchers

Radrangi/cloudml-dist-mnist-example

Radrangi/CS-229

Assignment Solutions to Coursera CS-229 Machine Learning by Stanford

Radrangi/Data-Analysis-and-Machine-Learning-Projects

Repository of teaching materials, code, and data for my data analysis and machine learning projects.

Radrangi/data-science-your-way

Ways of doing Data Science Engineering and Machine Learning in R and Python

Radrangi/datalab-samples

Radrangi/DataSciencePython

common data analysis and machine learning tasks using python

Radrangi/DCGAN-tensorflow

A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"

Radrangi/deep-q-atari

Keras and OpenAI Gym implementation of the Deep Q-learning algorithm to play Atari games.

Radrangi/DeepLearnToolbox

Matlab/Octave toolbox for deep learning. Includes Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders and vanilla Neural Nets. Each method has examples to get you started.

Radrangi/DL_MODIS

Test based on the code of: Rußwurm M., Körner M. (2017). Temporal Vegetation Modelling using Long Short-Term Memory Networks for Crop Identification from Medium-Resolution Multi-Spectral Satellite Images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017.

Radrangi/domain-transfer-network

TensorFlow Implementation of "Unsupervised Cross-Domain Image Generation"

Radrangi/example-project

Example Python DS project

Radrangi/Face-Recognition

FACE RECOGNITION ---------------- The Yale Face Database contains 165 grayscale images in GIF format of 15 individuals. There are 11 images per subject, one per different facial expression or configuration: center-light, w/glasses, happy, left-light, w/no glasses, normal, right-light, sad, sleepy, surprised, and wink. Your tasks are the following: 1. I have divided image into small blocks and extracted local binary patterns (LBP) from each block. Concatenated all LBP histograms to make a feature vector of an image. 2. Another feature vector is created out of gray levels of integral image. 3. Finally gray levels of image have been used as the last feature vector. 4. After Concatenating all feature vectors. I have Taken four images of each person for testing and the rest as training examples. 5. Using PCA to classify image for one-verses all classification scheme, i have shown results for few images that are selected randomly and reported the accuracy for all testing images using individual feature sets (gray level, integral, and LBP separately) and also for concatenated feature sets.

Radrangi/Global-Temperature-Change-Prediction

A Data Science project that uses an ARIMA model for Time Series Forecasting, to predict the temperature of any given city across a specific time period.

Radrangi/iconcolor

Automatic icon colorization using deep convolutional neural networks. "Towards Icon Design Using Machine Learning." In Stanford CS229, Fall 2017.

Radrangi/ipython-soccer-predictions

Sample iPython notebook with soccer predictions

Radrangi/machine-learning-classify-handwritten-digit

Classify handwritten digits using machine learning techniques Yan Liang, Yunzhi Wang and Delong Zhao Project scope For our machine learning project, we propose to build several machine learning classifiers that recognize handwritten digits. Handwritten digit recognition is a classic problem in machine learning studies for many years. We plan to do several experiments using different machine learning algorithms and compare the pattern recognition performance. We hope to create a classifier that has same or better categorization accuracy than record performance from previous studies. Yan will focus on neural network, Delong will focus on the random forests methods, and Yunzhi will focus on SVMs and KNNs. We will also develop a final novel classifier that combines the best models from our different experiments. We hypothesize that the final classifier will archive a categorization accuracy of 0.99. This indicates that the classifier correctly classified all the handwritten digits but 1% of the images. The goal of handwritten digit recognition is to determine what digit is from an image of a single handwritten digit. It can be used to test pattern recognition theories and machine learning algorithms. Preprocessed standard handwritten digit image database has been developed to compare different digit recognizers. In our semester project, we will use modified National Institute of Standards and Technology (MNIST) handwritten digit images dataset from kaggle digit recognizer project. The Kaggle MNIST dataset is freely available and collected 28,000 training images and 42,000 test images. Each image is a preprocessed single black and white digit image with 28 x 28 pixels. Each pixel is an integer value range from 0 to 255 which represent the brightness of the pixel, the higher value meaning darker. Each image also has a label which is the correct digit for the handwritten image. For each input handwritten image, our model will output which digit we predict and evaluate with the correct label. We will use 28,000 training images to train our machine learning model and use 42,000 test images to test the performance. Then we will calculate the percentage of the test images that are correctly classified and compare the performance of different machine learning algorithms.

Radrangi/mooc-setup

Information for setting up for the BerkeleyX Spark Intro MOOC, and lab assignments for the course

Radrangi/pattern-recognition

Imagery Projet: Analysis of histopathological images in order to automatically detect structure of interest

Radrangi/Practical-Data-Science-Cookbook-Second-Edition

Practical Data Science Cookbook, Second Edition, published by Packt

Radrangi/Python

Python script and Documents

Radrangi/python-algorithms

Collection of algorithm implementations from various sources plus own creations.

Radrangi/Python-Machine-Learning-By-Example

Python Machine Learning By Example, published by Packt

Radrangi/spark-training

Spark training material

Radrangi/TensorKart

self-driving MarioKart with TensorFlow