Search for: All records

Abstract There is a growing demand for low-power, autonomously learning artificial intelligence (AI) systems that can be applied at the edge and rapidly adapt to the specific situation at deployment site. However, current AI models struggle in such scenarios, often requiring extensive fine-tuning, computational resources, and data. In contrast, humans can effortlessly adjust to new tasks by transferring knowledge from related ones. The concept of learning-to-learn (L2L) mimics this process and enables AI models to rapidly adapt with only little computational effort and data. In-memory computing neuromorphic hardware (NMHW) is inspired by the brain’s operating principles and mimics its physical co-location of memory and compute. In this work, we pair L2L with in-memory computing NMHW based on phase-change memory devices to build efficient AI models that can rapidly adapt to new tasks. We demonstrate the versatility of our approach in two scenarios: a convolutional neural network performing image classification and a biologically-inspired spiking neural network generating motor commands for a real robotic arm. Both models rapidly learn with few parameter updates. Deployed on the NMHW, they perform on-par with their software equivalents. Moreover, meta-training of these models can be performed in software with high-precision, alleviating the need for accurate hardware models. 

\We show that braid varieties for any complex simple algebraic group G are cluster varieties. This includes open Richardson varieties inside the flag variety G/B. 

In response to COVID-19, the CDC issued hygiene, protective equipment, and physical distancing guidelines to reduce virus transmission. Adherence was crucial for public health, particularly in the earliest stage of COVID-19, before effective treatments emerged. Still, there was wide variation in willingness and/or ability to follow the recommendations. One group that might be expected to flout rules and take risks under normal circumstances is adolescents. This developmental stage predisposes one to push boundaries and seek the company of peers. Adolescents with a history of lawbreaking might be even more inclined to disregard public health guidelines due to experiential and dispositional factors. We employed a longitudinal study launched prior to the pandemic to identify which pre-pandemic factors predict adolescents’ adherence to—or disregard for—public health guidelines during a crisis. The sample (N = 75, 30% justice-involved) came from predominantly minoritized communities in a southwestern U.S. city. Data were collected in three waves over one year. Analyses tested whether adherence varied by time period, local infection trajectories, justice involvement, pre-pandemic mental health, risk-taking, and rule orientation. Results revealed that adherence declined over time and was generally lower among justice-involved adolescents. In addition, justice-involved adolescents with higher depressive symptoms displayed lower adherence, whereas those reporting higher anxiety symptoms displayed higher adherence. Understanding these factors is crucial for developing strategies to promote adherence to public health guidelines among adolescents during public health emergencies. 

Abstract The learning and recognition of object features from unregulated input has been a longstanding challenge for artificial intelligence systems. Brains, on the other hand, are adept at learning stable sensory representations given noisy observations, a capacity mediated by a cascade of signal conditioning steps informed by domain knowledge. The olfactory system, in particular, solves a source separation and denoising problem compounded by concentration variability, environmental interference, and unpredictably correlated sensor affinities using a plastic network that requires statistically well-behaved input. We present a data-blind neuromorphic signal conditioning strategy, based on the biological system architecture, that normalizes and quantizes analog data into spike-phase representations, thereby transforming uncontrolled sensory input into a regular form with minimal information loss. Normalized input is delivered to a column of spiking principal neurons via heterogeneous synaptic weights; this gain diversification strategy regularizes neuronal utilization, yoking total activity to the network’s operating range and rendering internal representations robust to uncontrolled open-set stimulus variance. To dynamically optimize resource utilization while balancing activity regularization and resolution, we supplement this mechanism with a data-aware calibration strategy in which the range and density of the quantization weights adapt to accumulated input statistics.