Large deep learning models have achieved significant success in various tasks. However, the performance of a model can significantly degrade if it is needed to train on datasets with noisy labels with misleading or ambiguous information. To date, there are limited investigations on how to restore performance when model degradation has been incurred by noisy label data. Inspired by the ``forgetting mechanism'' in neuroscience, which enables accelerating the relearning of correct knowledge by unlearning the wrong knowledge, we propose a robust model restoration and refinement (MRR) framework COLUR, namely Confidence-Oriented Learning, Unlearning and Relearning. Specifically, we implement COLUR with an efficient co-training architecture to unlearn the influence of label noise, and then refine model confidence on each label for relearning. Extensive experiments are conducted on four real datasets and all evaluation results show that COLUR consistently outperforms other SOTA methods after MRR.

Patients with semantic dementia (SD) present with remarkably consistent atrophy of neurons in the anterior temporal lobe and behavioural impairments, such as graded loss of category knowledge. While relearning of lost knowledge has been shown in acute brain injuries such as stroke, it has not been widely supported in chronic cognitive diseases such as SD. Previous research has shown that deep linear artificial neural networks exhibit stages of semantic learning akin to humans. Here, we use a deep linear network to test the hypothesis that relearning during disease progression rather than particular atrophy cause the specific behavioural patterns associated with SD. After training the network to generate the common semantic features of various hierarchically organised objects, neurons are successively deleted to mimic atrophy while retraining the model. The model with relearning and deleted neurons reproduced errors specific to SD, including prototyping errors and cross-category confusions. This suggests that relearning is necessary for artificial neural networks to reproduce the behavioural patterns associated with SD in the absence of \textit{output} non-linearities. Our results support a theory of SD progression that results from continuous relearning of lost information. Future research should revisit the role of relearning as a contributing factor to cognitive diseases.

After decades spent discussing how and what to teach in the classrooms, the focus is now turning more to implementation, experts said at the World Innovation Summit for Education (WISE) conference in Doha, hosted by the Qatar Foundation on 19-21 November. Ministers and education experts discussed in Doha how to reap the benefits of the digital revolution as new challenges arise from teaching students across the world in the era of artificial intelligence. OECD countries spend on average 4.5% of their GDP on education. At the same time, education itself is transforming to adapt to a changing planet. The constant retooling of labour skills will be a central element of a European Commission paper on the future of the EU social pillar, to be published on 26 April, EURACTIV.com In an increasingly uncertain and unstable world, citizens are expected to become life-long learners in order to remain relevant for a fast-changing labour market that will be disrupted by machines.