In this page you will find everything you need to know about my research interests and the work I’m carrying on in my daily activities as a PhD Student. I’m always looking for collaboration and open for discussion. Fell free to drop me a line at anytime! ;-)
I have a strong background in Data mining and Machine Learning. I have always felt at ease in manipulating, managing and analyzing large collections of data and I have successfully applied this knowledge in the context of biological systems. My own interest has then evolved towards the huge field of Artificial Intelligence, having always been intrigued by the idea of building a machine with superhuman abilities. I am now fully engaged in the study of Deep Learning, Continuous/Lifelong learning, and their application in Computer Vision and Internet-Of-Things.
My interest is currently focused on trying to answer to the following questions:
How much biological learning systems can inspire us to build better machines and better learning algorithms? What is the right level of abstraction? Can recent advances in Neuroscience provide useful insights to better understand what intelligence really is and design smart algorithms accordingly?
What does it really mean unsupervised learning? How much is it important for a learning algorithm? Is it the main feature our brain uses to solve almost any new problem it encounters?
How much incremental and continuous learning philosophies should be embraced? Are them useful to help generalizing a learning algorithm?
How currently models can be scaled and shaped towards a single and flexible universal learning algorithm? How to automatically discover classes and adjust the architecture to solve a task previously unknown?
I’m currently working on the following projects:
Evaluating and comparing HTMs and CNNs in continuous/lifelong learning scenarios. I’m currently working to evaluate and compare HTMs and CNNs in continuous/lifelong learning scenarios. This is intriguing for the very nature of the task, which has a biological plausibility. We are primarily focused on tasks in Computer Vision which include temporal coherent data stream.
Scaling up the HTM algorithm. Another interesting project I’m working on is specifically releated to the HTM algorithm. Despite CNNs, the HTM algorithm is still very young. The main effort is focused on saling up both the algorithm and the implementation to work with images greater than 64x64 pixels and possibily with colors.
New benchmark for temporal coherent learning algorithms. Temporal coherence has already shown in the past to be a good surrogate of a supervised signal. However, in letterature there are few example of simple and open video benchmark for object recognition. The main goal of this project is to create a new benchmark to train deep learning models using temporal coherence.
Exporting our computer vision experiments to the Nao Robot platform. Another important project we’re starting to explore concerns the validation of our algorithms in a robotic context. Since we are mainly interested in biologically inspired deep learning methods, this would be the next necessary step to validate our research.
Smartphone sensors based methods for transportation mode detection. In this more applicative project the main goal is to detect the mobility of the users based only on (low battery consumption) sensors embedded in their mobile phone. The streaming nature of the training data in this task, makes it the natual playfield to test our continuos/online Machine Learning and Deep Learning algorithms.
All the past projects as a graduate and PhD student are available at my Linkedin page!