STUDENT

OPPORTUNITIES

Rulex is always eager to welcome students for internships and thesis work. We believe it is a win win opportunity for everyone.

For students, who can quickly grow coached by experienced colleagues, understand their aspirations and be readier to enter the world of work.

For Rulex, which can leverage the new ideas and the enthusiasm of young talents to improve its products and explore new opportunities.

And it is also a unique opportunity to gradually enter the Rulex world and grow up as a Rulexer.
Have a look at the projects below and contact us if you have questions. Or, if you have some brilliant idea, you can also propose your own project.

=

ADVERSARIAL ATTACK EFFECT ON CLASSIFICATION PERFORMANCE (M.SC./B.SC.)

Recently, research in the machine learning field is also focusing on the fact that algorithms can be tricked into making a wrong prediction, by adding a relatively small, but carefully designed noise to the test set: this action is known as an adversarial attack. It is then increasingly relevant to evaluate the robustness of different algorithms with respect to this kind of attacks. The student will perform these activities:

  • Study a way to evaluate different adversarial attacks
  • Implement a subset of these techniques
  • Design a case study to evaluate the impact of (different kinds of) adversarial attacks on the performance of different classification algorithms
  • Perform the tests and evaluate the results

GO TO APPLY FORM

=

BIO-INSPIRED OPTIMIZATION AND RULE-BASED CONTROL ON TRANSPORT SCHEDULING OPTIMIZATION (M. SC)

Bio-Inspired methods allow to optimize also complex systems when the optimum cannot be found with exact approaches. They are inspired by some natural process, such as Charles Darwin’s evolution theory. On the other side Rule-Based Control aims at optimizing complex systems by using a rule-based model obtained directly by the data. In this way, an explicit form of the cost function is not needed, increasing the range of potential applications. In this project the student will:

  • Study the state-of-the-art of Bio-Inspired methods
  • Definition of a case study in the field of public transport scheduling
  • Developing analysis workflows for optimizing the network
  • Analysing the results and optimizing the performances

GO TO APPLY FORM

=

DATA DRIVEN RULE-GENERATION METHODS FOR THE VERIFICATION AND VALIDATION OF CYBER-PHYSICAL SYSTEMS (M.SC.)

Verification and Validation (V&V) consists in ensuring that automated systems function in the intended way according to Safety, Cybersecurity and Privacy (SCP) requirements. The increasing integration and interconnection of modern Cyber-Physical Systems (CPS) incus an overhead on the V&V process making it time-consuming and costly. Machine learning can be applied to reduce the complexity of the V&V process highlighting more risky situations, that could better be investigated through standard techniques. During the thesis, the student will:

  • Study the state of the art of Verification and Validation techniques
  • Study the state of thew art of machine learning application in V&V
  • Develop novel approaches based on the combination between standard V&V methods and rule-based machine learning techniques.
  • Test the new approaches on some datasets and evaluate the results in terms of precision and computational effort.

GO TO APPLY FORM

=

EVALUATING THE STABILITY OF TIME-DEPENDENT SET OF RULES (M.SC./B.SC.)

Rule-based decision methods are becoming crucial in modern process automation system since they allow expert users to understand the mechanism used by the machine to take decisions. Moreover, integration to manual rules (discovered by humans) and automatic rules (discovered by the machine) is a key point for improving automatic decision processes. To this aim, it is essential to transform the space of the rules into a metric space, in order to allow operations such as distance computation.

The student will:

  • Study a way to evaluate the distance between sets of rules.
  • Implement these definitions.
  • Design a case study to evaluate the effectiveness of this approach.
  • Perform the tests and evaluate the results.

GO TO APPLY FORM

=

IMPROVING THE PERFORMANCES OF RULE-BASED MACHINE LEARNING METHODS THROUGH A SEQUENTIAL ENSEMBLE APPROACH (M.SC./B.SC.)

Explainability of machine learning algorithms is one of the most important challenges in today Artificial Intelligence. As a matter of fact, understandable models can be audited by expert human users, allowing a quicker and sounder implementation in automated decision systems. Rulex has developed an innovative rule-based machine learning algorithm, named Logic Learning Machine. The objective of the thesis is to develop an algorithm independent sequential ensemble approach and to apply it to Logic Learning Machine to improve the prediction ability. These are the main activities:

  • Using the Rulex platform, developing a workflow for the generation of ensembles of classifiers and sequentially applying them to a dataset
  • Applying this workflow to Logic Learning Machin
  • Test the approach to some benchmark dataset and compare with results obtained with standard methods

GO TO APPLY FORM

=

MISSING IMPUTATION EFFECT ON CLASSIFICATION PERFORMANCE (B.SC.)

Often, when statistical and machine learning techniques are applied to real-world data, the data analyst needs to face the fact that at least some of the features include missing values. Excluding samples including missing features from the analysis can significantly decrease, even up to the point to make this choice unfeasible. To this end, missing imputation techniques such as MICE (Multiple Imputation by Chained Equation) have been developed. Of course, the adoption and tuning of one of such techniques is expected to have an impact on the performance of the following modelling phase. The student will:

  • Study a way to evaluate different techniques of missing imputation
  • Implement a subset of these techniques
  • Design a case study to evaluate the impact of (different kinds of) missing imputation on the performance of different classification algorithms
  • Perform the tests and evaluate the results

GO TO APPLY FORM

=

RULE-BASED METHODS FOR UNSUPERVISED DETECTION OF ANOMALIES (M.SC.)

Detecting anomalies in a set of data is a crucial task almost all application field. Sometimes anomalies are manually flagged by human users that, thanks to their experience, are able to distinguish regular cases from anomalous ones. Nevertheless, in most cases anomalies are hidden in the data and should be discovered without any human supervision. For this reason, unsupervised methods for anomaly detection have been extensively studied in the last years. One possible choice is given by auto-encoding methods that compare the prediction provided by supervised methods with the actual one to determine the level of anomaly of a pattern. Different supervised methods can be used in this context. In this thesis the student will explore the possibility of using a rule-based classification method. In particular, the student will:

  • Study a way to use autoencoding rule-based methods to detect anomalies.
  • Implement these definitions.
  • Design a case study to evaluate the effectiveness of this approach.
  • Perform the tests and evaluate the results.

GO TO APPLY FORM

=

RULE-BASED ROBOTIC DATA CORRECTION (M.SC.)

The problem of incorrect data is a big challenge for most companies since it affects all the data-based decision processes resulting in higher costs. Robotic Data Correction (RDC) is an innovative tool, developed by Rulex, to automatically correct data. RDC is a general-purpose tool that corrects also interdependent errors in data. The activities to be carried in the thesis are related to one or more of these objectives:

  • Exploring new applications of RDC.
  • Extending the application of RDC to ordered variables.
  • Developing analysis workflow ready to be deployed in real world scenarios.

The candidate will study how RDC works, develop some improvements to the current methods and test their effectiveness on real world and/or synthetic data.

GO TO APPLY FORM

Fill the application form


Please upload your CV in PDF format only (3Mb max file upload).



Message

Feel free to ask a question or simply leave a comment.



click HERE to read our Privacy Policy page