Olga Lyudchik

Working on investigation of stream-based machine learning techniques for anomaly detection scenarios (Python, Scala): • Application of existing machine learning algorithms and frameworks in streaming environments (Apache Flink and Apache Spark) • Implementation of batch-driven as well as online machine learning models for the aforementioned DSPEs • Evaluation and comparison of both implementations with respect to their scalability and modelling capabilities

Was working on definition and implementation of a machine learning system for the detection of abnormal behaviour within the LogMeIn RTC infrastructure (Python): • Applied deep learning-based anomaly detection techniques with AWS Sagemaker and Tensorflow • Collected anomalies in audio quality data and validated the system with them using statistical methods • Performed hyperparameter tuning job of models using Bayesian optimization in Sagemaker

Was working in a research group on developing a method for recording information inside optically transparent materials, based on the phenomenon of laser breakdown and precision laser treatment (MATLAB).

Was working in a Caltech Group at LHC's CMS Detector on developing new machine learning algorithms for outlier detection using deep autoencoder (Python). Attended a series of lectures, discussion sessions on a wide range of topics in the fields of physics and computing.

Was working on creating an application with a GUI running on the Host-PC to interact with FPGA device over Ethernet (Qt C++): • Provided a terminal to transmit simple text messages to the FPGA device and captured the response • Acquired a fast incoming data stream from the FPGA device • Showed the data in the oscilloscope graph in real-time • Calculated the FFT of the shown signal