More Like this

1. A Simple, Fast Algorithm for Continual Learning from High-Dimensional Data

   Ashtekar, Neil; Honavar, Vasant G (May 2023, Eleventh International Conference on Learning Representations)

   As an alternative to resource-intensive deep learning approaches to the continual learning problem, we propose a simple, fast algorithm inspired by adaptive resonance theory (ART). To cope with the curse of dimensionality and avoid catastrophic forgetting, we apply incremental principal component analysis (IPCA) to the model's previously learned weights. Experiments show that this approach approximates the performance achieved using static PCA and is competitive with continual deep learning methods. Our implementation is available on https://github.com/neil-ash/ART-IPCA 

   more » « less
2. On-Device Continual Learning With STT-Assisted-SOT MRAM Based In-Memory Computing

   https://doi.org/10.1109/TCAD.2024.3371268  

   Zhang, Fan; Sridharan, Amitesh; Hwang, William; Xue, Fen; Tsai, Wilman; Wang, Shan Xiang; Fan, Deliang (February 2024, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems)

   Due to the separate memory and computation units in traditional Von-Neumann architecture, massive data transfer dominates the overall computing system’s power and latency, known as the ‘Memory-Wall’ issue. Especially with ever-increasing deep learning-based AI model size and computing complexity, it becomes the bottleneck for state-of-the-art AI computing systems. To address this challenge, In-Memory Computing (IMC) based Neural Network accelerators have been widely investigated to support AI computing within memory. However, most of those works focus only on inference. The on-device training and continual learning have not been well explored yet. In this work, for the first time, we introduce on-device continual learning with STT-assisted-SOT (SAS) Magnetic Random Access Memory (MRAM) based IMC system. On the hardware side, we have fabricated a SAS-MRAM device prototype with 4 Magnetic Tunnel Junctions (MTJ, each at 100nm × 50nm) sharing a common heavy metal layer, achieving significantly improved memory writing and area efficiency compared to traditional SOT-MRAM. Next, we designed fully digital IMC circuits with our SAS-MRAM to support both neural network inference and on-device learning. To enable efficient on-device continual learning for new task data, we present an 8-bit integer (INT8) based continual learning algorithm that utilizes our SAS-MRAM IMC-supported bit-serial digital in-memory convolution operations to train a small parallel reprogramming Network (Rep-Net) while freezing the major backbone model. Extensive studies have been presented based on our fabricated SAS-MRAM device prototype, cross-layer device-circuit benchmarking and simulation, as well as the on-device continual learning system evaluation. 

   more » « less
3. How efficient are today’s continual learning algorithms?

   Harun, M.Y.; Gallardo, J.; Hayes, T.L.; Kanan, C. (July 2023, CVPR Workshop on Continual Learning in Computer Vision (CLVISION))

   Supervised Continual learning involves updating a deep neural network (DNN) from an ever-growing stream of labeled data. While most work has focused on overcoming catastrophic forgetting, one of the major motivations behind continual learning is being able to efficiently update a network with new information, rather than retraining from scratch on the training dataset as it grows over time. Despite recent continual learning methods largely solving the catastrophic forgetting problem, there has been little attention paid to the efficiency of these algorithms. Here, we study recent methods for incremental class learning and illustrate that many are highly inefficient in terms of compute, memory, and storage. Some methods even require more compute than training from scratch! We argue that for continual learning to have real-world applicability, the research community cannot ignore the resources used by these algorithms. There is more to continual learning than mitigating catastrophic forgetting. 

   more » « less
4. BrainWash: A Poisoning Attack to Forget in Continual Learning

   https://doi.org/10.1109/CVPR52733.2024.02271  

   Abbasi, Ali; Nooralinejad, Parsa; Pirsiavash, Hamed; Kolouri, Soheil (June 2024, IEEE)

   Continual learning has gained substantial attention within the deep learning community, offering promising solutions to the challenging problem of sequential learning. Yet, a largely unexplored facet of this paradigm is its susceptibility to adversarial attacks, especially with the aim of inducing forgetting. In this paper, we introduce “Brain-Wash,” a novel data poisoning method tailored to impose forgetting on a continual learner. By adding the Brain-Wash noise to a variety of baselines, we demonstrate how a trained continual learner can be induced to forget its previously learned tasks catastrophically, even when using these continual learning baselines. An important feature of our approach is that the attacker requires no access to previous tasks' data and is armed merely with the model's current parameters and the data belonging to the most recent task. Our extensive experiments highlight the efficacy of Brain Wash, showcasing degradation in performance across various regularization and memory replay-based continual learning methods. Our code is available here: https://github.com/mint-vuIBrainwash 

   more » « less
5. Avalanche: an End-to-End Library for Continual Learning

   Lomonaco, V.; Pellegrini, L.; Cossu, A.; Carta, A.; Graffieti, G.; Hayes, T.; De Lange, M.; Masana, M.; Pomponi, J.; Ven, G.; et al (January 2021, CLVISION)

   null (Ed.)

   Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing interest in continual learning, especially within the deep learning community. However, algorithmic solutions are often difficult to re-implement, evaluate and port across different settings, where even results on standard benchmarks are hard to reproduce. In this work, we propose Avalanche, an open-source end-to-end library for continual learning research based on PyTorch. Avalanche is designed to provide a shared and collaborative codebase for fast prototyping, training, and reproducible evaluation of continual learning algorithms. 

   more » « less