Related papers: MPCS: Neuroplastic Continual Learning via Multi-Co…

Continual learning aims to learn multiple tasks sequentially. A key challenge in continual learning is balancing between two objectives: retaining knowledge from old tasks (stability) and adapting to new tasks (plasticity). Experience…

As next-generation implantable brain-machine interfaces become pervasive on edge device, incrementally learning new tasks in bio-plasticity ways is urgently demanded for Neuromorphic chips. Due to the inherent characteristics of its…

The goal of Continual Learning (CL) is to continuously learn from new data streams and accomplish the corresponding tasks. Previously studied CL assumes that data are given in sequence nose-to-tail for different tasks, thus indeed belonging…

How can we build agents that keep learning from experience, quickly and efficiently, after their initial training? Here we take inspiration from the main mechanism of learning in biological brains: synaptic plasticity, carefully tuned by…

Learning-based lossless compressors play a crucial role in large-scale genomic database backup, storage, transmission, and management. However, their 1) inadequate compression ratio, 2) low compression \& decompression throughput, and 3)…

We introduce the percolation with plasticity (PWP) systems that exhibit neuromorphic functionalities including multi-valued memory, random number generation, matrix-vector multiplication, and associative learning. PWP systems have multiple…

Edge devices operating in dynamic environments critically need the ability to continually learn without catastrophic forgetting. The strict resource constraints in these devices pose a major challenge to achieve this, as continual learning…

Learning new information without forgetting prior knowledge is central to human intelligence. In contrast, neural network models suffer from catastrophic forgetting: a significant degradation in performance on previously learned tasks when…

Continual learning requires incremental compatibility with a sequence of tasks. However, the design of model architecture remains an open question: In general, learning all tasks with a shared set of parameters suffers from severe…

Catastrophic forgetting is one of the fundamental issues of continual learning because neural networks forget the tasks learned previously when trained on new tasks. The proposed framework is a new path-coordinated framework of continual…

Continual learning algorithms which keep the parameters of new tasks close to that of previous tasks, are popular in preventing catastrophic forgetting in sequential task learning settings. However, 1) the performance for the new continual…

Continual learning in artificial neural networks is fundamentally limited by the stability--plasticity dilemma: systems that retain prior knowledge tend to resist acquiring new knowledge, and vice versa. Existing approaches, most notably…

Model Predictive Control (MPC) provides interpretable, tunable locomotion controllers grounded in physical models, but its robustness depends on frequent replanning and is limited by model mismatch and real-time computational constraints.…

Continual learning, the ability to acquire and transfer knowledge through a models lifetime, is critical for artificial agents that interact in real-world environments. Biological brains inherently demonstrate these capabilities while…

Sensors and actuators based on resonant micro-electro-mechanical systems (MEMS), such as scanning micro mirrors, are well-established in automotive and consumer products. As the areas of application broaden, the requirements for the MEMS…

A supervised learning framework is proposed to approximate a model predictive controller (MPC) with reduced computational complexity and guarantees on stability and constraint satisfaction. The framework can be used for a wide class of…

We propose a novel approach to lifelong learning, introducing a compact encapsulated support structure which endows a network with the capability to expand its capacity as needed to learn new tasks while preventing the loss of learned…

While Model Predictive Control (MPC) enforces safety via constraints, its real-time execution can exceed embedded compute budgets. We propose a Barrier-integrated Adaptive Neural Model Predictive Control (BAN-MPC) framework that synergizes…

We develop a three-component Model Predictive Control (MPC) algorithm to achieve output-reference tracking with prescribed performance for continuous-time nonlinear systems. One component is so-called funnel MPC, which achieves reference…

Humans and animals learn throughout life. Such continual learning is crucial for intelligence. In this chapter, we examine the pivotal role plasticity mechanisms with complex internal synaptic dynamics could play in enabling this ability in…