Prediction-error driven memory consolidation for continual learning and adaptive greenhouse models

Check my AI Transfer work submitted to Springer KI (German Journal on Artificial Intelligence, special issue on Developmental Robotics) on “Prediction error-driven memory consolidation for continual learning”, applied on data from innovative greenhouses:

Episodic memory replay and prediction-error driven consolidation are used to tackle online learning in deep recurrent neural networks. Inspired by evidences from cognitive sciences and neuroscience, memories are retained depending on their congruency with prior knowledge.
This congruency is estimated in terms of prediction errors resulting from a generative model. In particular, our framework chooses which samples to maintain in the episodic memory based on their expected contribution to the learning progress.
Different retention strategies are compared. We analyse their impact on the variance of the samples stored in the memory and on the stability/plasticity of the model.

Co-authored with Luis Miranda and Uwe Schmidt, Humboldt-Universität zu Berlin.

SAGE Adaptive Behavior

Our article on “Intrinsic Motivation and Episodic Memories for Robot Exploration of High-Dimensional Sensory Spaces” is out in SAGE Adaptive Behaviour! Pre-print available here:

Co-authored with Antonio Pico (HU-Berlin), Verena Hafner (HU-Berlin), Peter Hanappe (Sony CSL), David Colliaux (Sony CSL) and Timothee Wintz (Sony CSL)

Intrinsic motivation and episodic memories for robot exploration on high dimensional sensory spaces

Check out my new work submitted to Adaptive Behaviours (Sage Journal) on Intrinsic motivation and episodic memories for robot exploration on high-dimensional sensory spaces:

The proposed framework adopts deep convolutional neural networks and shallow networks to generate curiosity-driven behaviours in a robot. Online learning of such models is performed. An episodic memory system is used to face catastrophic forgetting issues, typically experienced when performing online updates of artificial neural networks.

Workshop on “Predictive processes for motor and cognitive development in robots” at Sant’Anna

I am organising a workshop on “Predictive processes for motor and cognitive development in robots” as part of my Marie Sklodowska Curie project “Predictive Robots” at the BioRobotics Institute at Sant’Anna featuring invited talks from Prof. Bruno Lara (UAEM Mexico) and Dr. Alejandra Ciria (UAEM Mexico).

Download the flyer here. Download the full programme here.

Details follows!


Evidences from cognitive sciences and neurosciences suggest that several perceptual phenomena and cognitive capabilities would rely on processes of anticipation of sensorimotor activity. 

Different accounts on computational models for predictive processes have been proposed in the literature. This workshop provides an overview of established frameworks of predictive internal models – which are based on the idea that perception is a bottom-up flow of information sourced from sensory receptors – and of more recent proposals on predictive processing – where perception relies on deviations from top-down cortical predictions.

Moreover, this workshops aims at fostering discussions on the role that predictive processes may have in robotics, from supporting motor control and adaptive behaviours to enabling cognitive development.

Organised by Dr. Guido Schillaci as part of the EU-H2020 Marie Sklodowska Curie project “Predictive Robots”, this workshop will feature talks from two invited speakers, Prof. Bruno Lara (UAEM, Mexico, and Alexander von Humboldt fellow) and  Dr. Alejandra Ciria (UAEM and Humboldt-Universität zu Berlin), and from members of the BioRobotics Institute of the Scuola Superiore Sant’Anna.


Aula 3, The BioRobotics Institute, Viale Rinaldo Piaggio 34, Pontedera (Italy)


Friday, 22nd November 2019, 11:00am


11:00 Welcome by Guido Schillaci

11:10 Internal models and developmental robotics (Bruno Lara)

11:40 Internal models and prediction error dynamics (Alejandra Ciria)

12:10 Predictive processes and the minimal self (Guido Schillaci)

12:30 Combining prediction and adaptation for robot control (Lorenzo Vannucci)

12:50 Brain-inspired algorithms for robot control (Egidio Falotico)

13:10 Conclusions