Congratulations to Luigi di Sotto and Stefan Daniel Motoc for having completed their M.Sc. and B.Sc. in Computer Science with a final project on deep learning topics. Luigi discussed a novel pooling mechanism for graph convolutional networks. Stefan proposed a thorough analysis of the latent space of MusAE, our deep adversarial autoencoder for music generation.
Yearly Archives: 2019
Upcoming seminar on AI and arts
I will be delivering a talk on computational creativity through neural networks this week at the Museo degli Strumenti del Calcolo in Pisa. More info on the seminar and on the logistics in the following (in Italian I am afraid).
Creatività Artificiale: reti neurali, arte e probabilità
Mercoledì 29 maggio, ore 17:00
Museo degli Strumenti per il Calcolo, Pisa, 29 Maggio 2019
L’intelligenza artificiale può cimentarsi con una prerogativa così fortemente umana come la creatività artistica? La conferenza racconterà come le reti neurali profonde possano essere utilizzate per generare lavori artistici che, in alcuni casi, sono indistinguibili da opere dell’ingegno umano. Spiegheremo poi come la generazione di un’opera d’arte artificiale sia frutto di un processo matematico basato sulla statistica.
First graduate of the AI Curriculum
Congratulations to my student Vlad Pandelea who is hitting the University headline news as first graduate (cum laude!) of the Artificial Intelligence curriculum here at the Computer Science Department.
New M.Sc. Graduates!
Congratulations to Diego Giorgini and to Vlad Pandelea for having succesfully defended their theses on a multiscale recurrent neural memory and on audio-augmented dialogue systems.
Paper accepted @IJCNN 2019
A paper on Bayesian tensor factorization for efficient processing of structured data has just been accepted for IJCNN 2019. Check it out:
Bayesian Tensor Factorisation for Bottom-up Hidden Tree Markov Models. Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN 2019I) , IEEE, 2019.
New ML graduates
Congratulations to two of my students who succesfully defended their B.Sc. and M.Sc. theses with two excellent ML projects.
Lorenzo Marsicano developed microESN, a library for the development of recurrent neural networks in embedded systems with minimal memory and computational resources.
Andrea Valenti designed a new deep learning model for MIDI music generation, beautifully named MusAE, for Music Adversarial autoEncoder (and of course to honour Greek mythology).
Congratulations!!
First ISPR lecture
The first lecture of the 2019 edition of the Intelligent Systems for Pattern Recognition (ISPR) course will be on
THURSDAY 22/02/2019 h. 14-16 – ROOM C1 – POLO FIBONACCI
More information on the course website.
New IEEE TNNLS journal paper
Congratulations to my student Francesco Crecchi for his first journal paper showing how Dropout can be used to enforce robustness to missing inputs at test time in several recurrent neural networks. Check out its applications to sensor data processing.
Augmenting Recurrent Neural Networks Resilience by Dropout. In: IEEE Transactions on Neural Networs and Learning Systems, 2019.
Invited Lecture @ CALDAM Pre-School
Looking forward to delivering an invited lectured on deep learning for graphs at next week’s CALDAM 2019 pre-conference school in Kharagpur.
Paper accepted for ICRA 2019
A joint paper with the Hands and Haptics team at Centro Piaggio has just been accepted at the top-robotic confrence ICRA 2019 (and jointly to the IEEE Robotics and Automation Letters journal). A deep neural network learning, from humans, how to guide a robot arm in the manipulation of never-seen-before objects. Early access to the paper here: check out the upcoming videos of our system at work!
Learning from humans how to grasp: a data-driven architecture for autonomous grasping with anthropomorphic soft hands. In: IEEE Robotics and Automation Letters, pp. 1-8, 2019, ISSN: 2377-3766, (Also accepted for presentation at ICRA 2019).