Author name cluster

Nick Cheney

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

ECAI Conference 2024 Conference Paper

Reset It and Forget It: Relearning Last-Layer Weights Improves Continual and Transfer Learning

Lapo Frati
Neil Traft
Jeff Clune
Nick Cheney

This work identifies a simple pre-training mechanism that leads to representations exhibiting better continual and transfer learning. This mechanism—the repeated resetting of weights in the last layer, which we nickname “zapping”—was originally designed for a meta-continual-learning procedure, yet we show it is surprisingly applicable in many settings beyond both meta-learning and continual learning. In our experiments, we wish to transfer a pre-trained image classifier to a new set of classes, in few shots. We show that our zapping procedure results in improved transfer accuracy and/or more rapid adaptation in both standard fine-tuning and continual learning settings, while being simple to implement and computationally efficient. In many cases, we achieve performance on par with state of the art meta-learning without needing the expensive higher-order gradients by using a combination of zapping and sequential learning. An intuitive explanation for the effectiveness of this zapping procedure is that representations trained with repeated zapping learn features that are capable of rapidly adapting to newly initialized classifiers. Such an approach may be considered a computationally cheaper type of, or alternative to, meta-learning rapidly adaptable features with higher-order gradients. This adds to recent work on the usefulness of resetting neural network parameters during training, and invites further investigation of this mechanism.

Details

JBHI Journal 2024 Journal Article

The ChAMP App: A Scalable mHealth Technology for Detecting Digital Phenotypes of Early Childhood Mental Health

Bryn C. Loftness
Julia Halvorson-Phelan
Aisling O'Leary
Carter Bradshaw
Shania Prytherch
Isabel Berman
John Torous
William E. Copeland

Childhood mental health problems are common, impairing, and can become chronic if left untreated. Children are not reliable reporters of their emotional and behavioral health, and caregivers often unintentionally under- or over-report child symptoms, making assessment challenging. Objective physiological and behavioral measures of emotional and behavioral health are emerging. However, these methods typically require specialized equipment and expertise in data and sensor engineering to administer and analyze. To address this challenge, we have developed the ChAMP (Childhood Assessment and Management of digital Phenotypes) System, which includes a mobile application for collecting movement and audio data during a battery of mood induction tasks and an open-source platform for extracting digital biomarkers. As proof of principle, we present ChAMP System data from 101 children 4–8 years old, with and without diagnosed mental health disorders. Machine learning models trained on these data detect the presence of specific disorders with 70–73% balanced accuracy, with similar results to clinical thresholds on established parent-report measures (63–82% balanced accuracy). Features favored in model architectures are described using Shapley Additive Explanations (SHAP). Canonical Correlation Analysis reveals moderate to strong associations between predictors of each disorder and associated symptom severity (r =. 51–. 83). The open-source ChAMP System provides clinically-relevant digital biomarkers that may later complement parent-report measures of emotional and behavioral health for detecting kids with underlying mental health conditions and lowers the barrier to entry for researchers interested in exploring digital phenotyping of childhood mental health.

Details DOI

JBHI Journal 2021 Journal Article

Wearables and Deep Learning Classify Fall Risk From Gait in Multiple Sclerosis

Brett M. Meyer
Lindsey J. Tulipani
Reed D. Gurchiek
Dakota A. Allen
Lukas Adamowicz
Dale Larie
Andrew J. Solomon
Nick Cheney

Falls are a significant problem for persons with multiple sclerosis (PwMS). Yet fall prevention interventions are not often prescribed until after a fall has been reported to a healthcare provider. While still nascent, objective fall risk assessments could help in prescribing preventative interventions. To this end, retrospective fall status classification commonly serves as an intermediate step in developing prospective fall risk assessments. Previous research has identified measures of gait biomechanics that differ between PwMS who have fallen and those who have not, but these biomechanical indices have not yet been leveraged to detect PwMS who have fallen. Moreover, they require the use of laboratory-based measurement technologies, which prevent clinical deployment. Here we demonstrate that a bidirectional long short-term (BiLSTM) memory deep neural network was able to identify PwMS who have recently fallen with good performance (AUC of 0. 88) based on accelerometer data recorded from two wearable sensors during a one-minute walking task. These results provide substantial improvements over machine learning models trained on spatiotemporal gait parameters (21% improvement in AUC), statistical features from the wearable sensor data (16%), and patient-reported (19%) and neurologist-administered (24%) measures in this sample. The success and simplicity (two wearable sensors, only one-minute of walking) of this approach indicates the promise of inexpensive wearable sensors for capturing fall risk in PwMS.

Details DOI

ECAI Conference 2020 Conference Paper

Learning to Continually Learn

Shawn Beaulieu
Lapo Frati
Thomas Miconi
Joel Lehman
Kenneth O. Stanley
Jeff Clune
Nick Cheney

Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it. Much work has gone towards preventing the default tendency of machine learning models to catastrophically forget, yet virtually all such work involves manually-designed solutions to the problem. We instead advocate meta-learning a solution to catastrophic forgetting, allowing AI to learn to continually learn. Inspired by neuromodulatory processes in the brain, we propose A Neuromodulated Meta-Learning Algorithm (ANML). It differentiates through a sequential learning process to meta-learn an activation-gating function that enables context-dependent selective activation within a deep neural network. Specifically, a neuromodulatory (NM) neural network gates the forward pass of another (otherwise normal) neural network called the prediction learning network (PLN). The NM network also thus indirectly controls selective plasticity (i. e. the backward pass of) the PLN. ANML enables continual learning without catastrophic forgetting at scale: it produces state-of-the-art continual learning performance, sequentially learning as many as 600 classes (over 9, 000 SGD updates).

Details

TCS Journal 2016 Journal Article

Topological evolution for embodied cellular automata

Nick Cheney
Hod Lipson

In this work we introduce a novel method for creating behaviors in cellular automata: optimizing the topology of the cellular substrate while maintaining a single simple update rule. We study the effect of altering the shape of a 3D cellular automaton and local signaling ability of each of its cells on the ability of that automaton as a whole to give rise to emergent locomotion behavior. This system optimizes for the physically embodied interactions between a cellular automaton with an external physically simulated world, rather than optimizing directly for a computational ability internal to the automaton itself. We give each cell in the automaton the ability to have an internal “excited” state, and also the ability to perform a physical action (volumetric contraction and expansion) as a result of that state. We then employ an evolutionary algorithm to optimize for the locomotion ability of the “robot” resulting from the behavior of this embodied automaton. We demonstrate a number of diverse topologies which lead to effective locomotion behaviors in this paradigm. We believe that creating complex behavior from simple rules in a complex substrate not only opens up questions about cellular automata, but also provides insights towards the study of morphological computation and embodied cognition.

Details DOI