activity
20172019
most citedGradual Tuning: a better way of Fine Tuning the parameters of a Deep Neural Network

5 citations · 5 across the 3 of their papers we have counts for

collaborators

6 papers

cs.AI2019

Learning abstract perceptual notions: the example of space

Alexander V. Terekhov, J. Kevin O'Regan

Humans are extremely swift learners. We are able to grasp highly abstract notions, whether they come from art perception or pure mathematics. Current machine learning techniques de…

cs.LG2018

Learning agent's spatial configuration from sensorimotor invariants

Alban Laflaquière, J. Kevin O'Regan, Sylvain Argentieri +2

The design of robotic systems is largely dictated by our purely human intuition about how we perceive the world. This intuition has been proven incorrect with regard to a number of…

cs.LG2018

Learning an internal representation of the end-effector configuration space

Alban Laflaquière, Alexander V. Terekhov, Bruno Gas +1

Current machine learning techniques proposed to automatically discover a robot kinematics usually rely on a priori information about the robot's structure, sensors properties or en…

q-bio.NC2017

Why early tactile speech aids may have failed: no perceptual integration of tactile and auditory signals

Aurora Rizza, Alexander V. Terekhov, Guglielmo Montone +2

Tactile speech aids, though extensively studied in the 1980s and 90s, never became a commercial success. A hypothesis to explain this failure might be that it is difficult to obtai…

cs.NE2017

Block Neural Network Avoids Catastrophic Forgetting When Learning Multiple Task

Guglielmo Montone, J. Kevin O'Regan, Alexander V. Terekhov

In the present work we propose a Deep Feed Forward network architecture which can be trained according to a sequential learning paradigm, where tasks of increasing difficulty are l…

cs.AI20175 cited

Gradual Tuning: a better way of Fine Tuning the parameters of a Deep Neural Network

Guglielmo Montone, J. Kevin O'Regan, Alexander V. Terekhov

In this paper we present an alternative strategy for fine-tuning the parameters of a network. We named the technique Gradual Tuning. Once trained on a first task, the network is fi…