Soumya Banerjee is a PhD student in the Department of Computer Science and Engineering at Indian Institute Of Technology Kanpur. His research interest ranges across Computer Vision, Deep Learning, Active Learning, and Machine Learning.

For the thesis, he is working on lifelong learning methods for deep neural networks. LifeLong learning (LLL), also referred to as incremental learning or continual learning, studies the problem of training a conventional deep neural network incrementally with the data coming sequentially from possibly an unbounded stream with the following constraints: (i) the neural network can have access to the current data only, and access to the previously observed data is forbidden, and (ii) the model should be able to adapt to the changes in the data distribution without suffering from catastrophic forgetting. Interested readers can check this link to get a brief overview of the existing works in this area: https://arxiv.org/abs/2301.11892