One of the major assets of deep neural networks is that when trained on large data sets (source data), their knowledge can be transferred to small datasets (target data). Transfer learning for deep neural networks can be simply performed by finetuning the network on the new data. This talk will introduce the research field of continual learning where the aim is to not only adapt to the target data but also keep the performance on the original source data.
Speaker: Joost van de Weijer (Computer vision center)
IIIA-CSIC
22nd February, 12:00
More information