Machine Learning Engineer based in Leipzig, Germany with experience in research work on time-series compression and projects in pose estimation and computer vision. Has worked with techniques and tools including compress…
Machine Learning Engineer based in Leipzig, Germany with experience in research work on time-series compression and projects in pose estimation and computer vision. Has worked with techniques and tools including compressive sensing, time-series forecasting, ARIMA, LSTM AutoEncoders, OpenPose, Tensorflow, and embedded systems. Educational background includes Computer Science Engineering studies at the National Engineering School of Sfax.
Scraping images from the net for 30 classes then cleaning and annotating them
Using Data Augmentation and Transfer Learning techniques to prevent overfitting and boost model's performance
Using the MobileNet architecture to perform real-time classification on mobile phones
Building the OpenPose project on a Jetson Nano Card with Python and Tensorflow.
Fine-tuning the hyperparameters to meet some specific needs.
Writing an easy-to-follow guide for novices to reimplement my work.
Scraping images from the net for 30 classes then cleaning and annotating them.
Using Data Augmentation and Transfer Learning techniques to prevent overfitting and boost model's performance.
Using the MobileNet architecture to perform real time classification on mobile phones.
Building the OpenPose project on a Jetson Nano Card with Python and Tensorflow
Fine-tuning the hyperparameters to meet some specific needs
Writing an easy-to-follow guide for novices to reimplement my work (check my GitHub account)
Acquiring a basic knowledge on the Compressive Sensing field.
Analyzing and forecasting Time-Series data.
Trying several Artificial Intelligence techniques (AutoEncoders, RNNA, LSTM AutoEncoders...) to boost the efficiency of Compressive Sensing based systems.
Establishing a comparative study to illustrate the advantages and disadvantages of each approach.
Acquiring a basic knowledge on the Compressive Sensing field
Analyzing and forecasting Time-Series data
Trying several Artificial Intelligence techniques (AutoEncoders, RNNA, LSTM AutoEncoders...) to boost the efficiency of Compressive Sensing based systems
Establishing a comparative study to illustrate the advantages and disadvantages of each approach
نظام التوظيف التشغيلي المعتمد على الذكاء الاصطناعي أولاً، الذي يوحّد ويؤتمت دورة التوظيف بالكامل للمؤسسات الحديثة حول العالم.
د.جوب منطقة حرة ذ.م.م. 2026 © جميع الحقوق محفوظة
