RESUMEN
Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to "real world" events, where the input distributions and tasks encountered by the deployed systems will not be limited to the original training context, and systems will instead need to adapt to novel distributions and tasks while deployed. This critical gap may be addressed through the development of "Lifelong Learning" systems that are capable of (1) Continuous Learning, (2) Transfer and Adaptation, and (3) Scalability. Unfortunately, efforts to improve these capabilities are typically treated as distinct areas of research that are assessed independently, without regard to the impact of each separate capability on other aspects of the system. We instead propose a holistic approach, using a suite of metrics and an evaluation framework to assess Lifelong Learning in a principled way that is agnostic to specific domains or system techniques. Through five case studies, we show that this suite of metrics can inform the development of varied and complex Lifelong Learning systems. We highlight how the proposed suite of metrics quantifies performance trade-offs present during Lifelong Learning system development - both the widely discussed Stability-Plasticity dilemma and the newly proposed relationship between Sample Efficient and Robust Learning. Further, we make recommendations for the formulation and use of metrics to guide the continuing development of Lifelong Learning systems and assess their progress in the future.
Asunto(s)
Educación Continua , Aprendizaje AutomáticoRESUMEN
The creation of machine learning algorithms for intelligent agents capable of continuous, lifelong learning is a critical objective for algorithms being deployed on real-life systems in dynamic environments. Here we present an algorithm inspired by neuromodulatory mechanisms in the human brain that integrates and expands upon Stephen Grossberg's ground-breaking Adaptive Resonance Theory proposals. Specifically, it builds on the concept of uncertainty, and employs a series of "neuromodulatory" mechanisms to enable continuous learning, including self-supervised and one-shot learning. Algorithm components were evaluated in a series of benchmark experiments that demonstrate stable learning without catastrophic forgetting. We also demonstrate the critical role of developing these systems in a closed-loop manner where the environment and the agent's behaviors constrain and guide the learning process. To this end, we integrated the algorithm into an embodied simulated drone agent. The experiments show that the algorithm is capable of continuous learning of new tasks and under changed conditions with high classification accuracy (>94%) in a virtual environment, without catastrophic forgetting. The algorithm accepts high dimensional inputs from any state-of-the-art detection and feature extraction algorithms, making it a flexible addition to existing systems. We also describe future development efforts focused on imbuing the algorithm with mechanisms to seek out new knowledge as well as employ a broader range of neuromodulatory processes.
Asunto(s)
Aprendizaje Automático/normas , Tiempo , IncertidumbreRESUMEN
Transcranial electrical stimulation (tES) during sleep has been shown to successfully modulate memory consolidation. Here, we tested the effect of short duration repetitive tES (SDR-tES) during a daytime nap on the consolidation of declarative memory of facts in healthy individuals. We use a previously described approach to deliver the stimulation at regular intervals during non-rapid eye movement (NREM) sleep, specifically stage NREM2 and NREM3. Similar to previous studies using tES, we find enhanced memory performance compared to sham both after sleep and 48 h later. We also observed an increase in the proportion of time spent in NREM3 sleep and SDR-tES boosted the overall rate of slow oscillations (SOs) during NREM2/NREM3 sleep. Retrospective investigation of brain activity immediately preceding stimulation suggests that increases in the SO rate are more likely when stimulation is delivered during quiescent and asynchronous periods of activity in contrast to other closed-loop approaches which target phasic stimulation during ongoing SOs.