PAlberto del Bimbo is Full Professor at the Department of Information Engineering of University of Firenze. He is the author of over 350 scietific papers in Computer Vision and Multimedia. He is the Director of NEMECH the New Media for Cultural Heritage Center at the Università di Firenze.
He was the Program Chair of ICPR 2016, ICPR 201, and ACM Multimedia 2008, and the General Chair of ICPR 2020, ICMR 2019, ECCV 2012, ICMR 2011, ACM Multimedia 2010, and IEEE ICMCS 1999.
He is the Editor in Chief of ACM TOMM Transactions on Multimedia Computing, Communications, and Applications and Associate Editor of MTAP AND PAAA journals. He was Associate Editor of IEEE Transactions on Pattern Analysis and Machine Intelligence and IEEE Transactions on Multimedia. Prof. Del Bimbo is IAPR Fellow and the recipient of the 2016 ACM SIGMM Award for Outstanding Technical Contributions to Multimedia Computing, Communications and Applications.
Memory Networks and attention
Neural networks with memory capabilities have been introduced to solve several machine learning problems which require to model sequential data such as time series.
The most common models are RNN, LSTM and their variants. More recently, alternative solutions namely Transformers and Memory Augmented
Neural Networks have been suggested with distinguishing characteristics. The former directly compares the elements in the input sequence through self-attention mechanisms. The latter uses an external element-wise addressable memory. The course compares and presents these
new memory networks models and their applications.