This project is available as a student work experience opportunity with HPCC Systems this summer. Curious about other projects we are offering? Take a look at our Ideas List. Find out about the HPCC Systems Summer Internship Program.
The project proposal application period for 2020 summer internships is now open. Please see our list of Available Projects. Contact the project mentor for more information and to discuss your ideas. You may suggest a project idea of your own but it must leverage HPCC Systems in some way. Contact us for support from an HPCC Systems mentor with experience in your chosen project area.
These projects involve the development of machine learning algorithms to extend the existing ECL-ML (ECL Machine Learning) on the HPCC Systems platform, using ECL and the underlying Parallel Block BLAS (PB-BLAS) infrastructure.
While the general purpose is to develop these algorithms mostly in ECL, using other languages that can be embedded in HPCC (Python, Java, Javascript, R, C++) is an acceptable option too. A few functions are C++ functions with a C++/ECL wrapper around them.
The HPCC Systems Machine Learning Library, is a work in progress. However, it already contains many classification, regression and clustering algorithms.
These projects are currently available in this area:
- Extend the HPCC Systems ML matrix operation to include complex numbers
- Implement an approximate n-tile algorithm
- Word Vectorization
- Applying HPCC Systems Word Vectors to SEC Filings
- Utilise time series analysis techniques such as Delay-Embedding and Box-Jenkins
- Implement a preprocessing bundle to prepare data for use with HPCC Systems ML modules
- Linear/Logistic Regression Enhancements
- Anomaly Detection Algorithms
- Generative Adversarial Networks (GANs)
- Adaptive Density Based Clustering
- Independence Testing Bundle
- Predictive Model Markup Language (PMML) Processor
Objectives for the ML functions
- To be able to handle large training sets in a timely manner by distributing the training set across the nodes of an HPCC System Thor cluster.
- To produce statistics that measure the goodness of the fit of models created by the ML functions
Available Resources
- Examples of existing code
- HPCC Systems Machine Learning documentation
- HPCC Systems Technical Poster Presentations
Machine learning projects previously completed by students
| Name | Project Title | Year Completed | Resources |
|---|---|---|---|
Huafu Hu Masters of Science | Analysing telematics data to support the connected cars industry | 2019 | Tech Talk Presentation, November 2019 Poster |
Christopher Connelly Data Scientist | Cleaning and analysis of collegiate soccer GPS data in HPCC Systems | 2019 | Tech Talk Presentation, November 2019 Poster Community Day presentation |
Robert Kennedy Masters in ComputerScience | Create HPCC Systems on Hyper V | 2019 | Tech Talk Presentation, September 2019 Poster Community Day presentation |
Vannel Zeufack Masters in Computer Science | Develop and assess unsupervised anomaly detection methods using HPCC Systems | 2019 | Tech Talk Presentation, September 2019 Poster |
Farah Alshanik PhD Computer Science | Domain based common words list using high dimensional representation of words | 2019 | Tech Talk Presentation, September 2019 Poster Community Day presentation |
A Suryanarayanan Bachelor of Engineering | Evaluation of machine learning algorithms | 2019 | Tech Talk Presentation, August 2019 Poster |
Muiredach O'Riain BSc in Music and Computing | Machine Learning and the Forensic Applications of Audio Classification: An exploration of the forensic applications of sound classification using Artificial Neural Networks | 2019 | Poster |
Akshar Prasad BTech in Computer Science RV College of Engineering (RVCE), Bengalaru, India | Fraud detection in value based cards | 2019 | Tech Talk Presentation, August 2019 Poster |
Farah Alshanik PhD Computer Science | Text Search Bundle - Implementation of Equivalence Terms | 2018 | |
Nicole Navarro MS in Data Science | Healthcare: High Risk Geo-Social Analysis (Drug Socialization) | 2018 | |
Robert Kennedy Masters in Computer Science | Begin development of a software library (consisting of ECL and Python code) that would provide HPCC Systems distributed neural network training | 2018 | |
Lili Xu PhD in Computer Science | Implementation of CLDA Topic ModelingAlgorithm in ECL-ML | 2018 | |
Soukaina Filali PhD Computer Science | Extension of KMeans clustering and KNN classifier to time series data model in ECL-ML | 2018 | Tech Talk held in September 2018 |
Shah Muhammad Hamdi PhD Computer Science, Data Mining Georgia State University | Dimensionality Reduction and Feature Selection in ECL-ML | 2018 | |
George Mathew PhD student in Computer Science | 2017 | ||
Sarthak Jain PhD student in Computer Science | Documentation Generator for ECL Code | 2017 | |
Lili Xu PhD in Computer Science | Implement a Latent Semantic Analysis Algorithm in ECL | 2017 | |
Vivek Nair PhD in Computer Science | Empower ECL-ML: How to make the HPCC Systems Machine Learning Library easier to use | 2016 | |
Lili Xu PhD in Computer Science | Implement a YinYang K-Means Clustering Algorithm in ECL | 2016 | |
Syed Rahman PhD Student | Implement the Converse Sparse Cholesky Selection Algorithm in ECL | 2016 | |
Shweta Oak Bachelor of Engineering | Analyse which algorithms may provide the best results for the implementation of Non-Negative Matrix Factorisations (NMF) in ECL | 2016 | |
Sarthak Jain PhD student in Computer Science | Add new statistics to the Linear and Logistic Regression Modules | 2015 | |
Syed Rahman PhD Student | Implement the CONCORD Algorithm | 2015 |