More Like this

1. Understanding Lifelong Learning and Skills Development: Lessons Learned from Practicing Civil Engineers

   https://doi.org/10.1061/(ASCE)EI.2643-9115.0000068  

   Froehle, Kamryn ; Dickman, Logan ; Phillips, Adam R. ; Murzi, Homero ; Paretti, Marie ( October 2022 , Journal of Civil Engineering Education)
2. Lifelong DP: Consistently Bounded Differential Privacy in Lifelong Machine Learning

   Lai, Phung ; Hu, Han ; Phan, NhatHai ; Jin, Ruoming ; Thai, My T. ; Chen, An ( January 2022 , Conference on Lifelong Learning Agents. PMLR.)
3. Lifelong DP: Consistently Bounded Differential Privacy in Lifelong Machine Learning

   Lai, Phung ; Hu, Han ; Phan, Hai ; Jin, Ruoming ; Thai, My ; Chen, An ( August 2023 , Proceedings of The 1st Conference on Lifelong Learning Agents)
4. LIFELONG DP: CONSISTENTLY BOUNDED DIFFERENTIAL PRIVACY IN LIFELONG MACHINE LEARNING

   Lai, Phung ; Hu, Han ; Phan, NhatHai ; Jin, Ruoming ; Thai, My T. ; Chen, An M. ( July 2022 , 1st Conference on Lifelong Learning Agents)

   Precup, Doina ; Chandar, Sarath ; Pascanu, Razvan (Ed.)

   In this paper, we show that the process of continually learning new tasks and memorizing previous tasks introduces unknown privacy risks and challenges to bound the privacy loss. Based upon this, we introduce a formal definition of Lifelong DP, in which the participation of any data tuples in the training set of any tasks is protected, under a consistently bounded DP protection, given a growing stream of tasks. A consistently bounded DP means having only one fixed value of the DP privacy budget, regardless of the number of tasks. To preserve Lifelong DP, we propose a scalable and heterogeneous algorithm, called L2DP-ML with a streaming batch training, to efficiently train and continue releasing new versions of an L2M model, given the heterogeneity in terms of data sizes and the training order of tasks, without affecting DP protection of the private training set. An end-to-end theoretical analysis and thorough evaluations show that our mechanism is significantly better than baseline approaches in preserving Lifelong DP. The implementation of L2DP-ML is available at: https://github.com/haiphanNJIT/PrivateDeepLearning. 

   more » « less
5. Exploring the associative learning capabilities of the segmented attractor network for lifelong learning

   https://doi.org/10.3389/frai.2022.910407  

   Jones, Alexander ; Jha, Rashmi ( August 2022 , Frontiers in Artificial Intelligence)

   This work explores the process of adapting the segmented attractor network to a lifelong learning setting. Taking inspirations from Hopfield networks and content-addressable memory, the segmented attractor network is a powerful tool for associative memory applications. The network's performance as an associative memory is analyzed using multiple metrics. In addition to the network's general hit rate, its capability to recall unique memories and their frequency is also evaluated with respect to time. Finally, additional learning techniques are implemented to enhance the network's recall capacity in the application of lifelong learning. These learning techniques are based on human cognitive functions such as memory consolidation, prediction, and forgetting. 

   more » « less