Incremental robot learning of new objects with fixed update time

By Raffaello Camoriano, Giulia Pasquale, Carlo Ciliberto, Lorenzo Natale, Lorenzo Rosasco, Giorgio Metta. 2016

44 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

CORe50: a New Dataset and Benchmark for Continuous Object Recognition (2017, background): “…Networks [23], Active Long Term Memory Networks [7], Adaptive Convolutional Neural Network [29], PathNet [5], Incremental Regularized Least Squares [3], Elastic Weight Consolidation [11], Encoder-based Lifelong Learning [28], etc. Elastic Weight Consolidation ( EWC ) appears particularly…”
Continual Learning for Robotics (2019, background): “, 2015; Lomonaco and Maltoni, 2016) iCubWorldTransformation X (Pasquale et al., 2016; Camoriano et al., 2017) LSUN X (Wu et al.”
Overcoming Catastrophic Forgetting for Continual Learning via Model Adaptation (2018, background): “, 2018) (active column is distilled into the knowledge base, taking care to protect any previously acquired skills), and incremental regularized least squares (Camoriano et al., 2017).”
Continual Learning Based on OOD Detection and Task Masking (2022, methodology): “2017) and knowledge distillation (Li and Hoiem 2016) to minimize the change to previous models are two popular approaches (Jung et al. 2016; Camoriano et al. 2017; Fernando et al. 2017; Rannen Ep Triki et al. 2017; Seff et al. 2017; Zenke, Poole, and Ganguli 2017; Kemker and Kanan 2018; Ritter, Bote”
Online Object and Task Learning via Human Robot Interaction (2018, methodology): “Different deep learning methods were proposed [6] [7] and evaluated on the ICUB World dataset.”
Learning To Learn Around A Common Mean (2018, background): “This approach brings a substantial improvement over learning the tasks in isolation – known as independent task learning (ITL) – especially when the sample size per task is small, a common setting in many applications [6, 27, 30].”
AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem? (2020, unknown): “object recognition [82], [83] and classification [84].”