Significance Synapses with high probability of neurotransmitter release ( P ᵣ) depress during prolonged activity, which reduces the faithful transfer of information. Auditory nerve synapses onto ...bushy cells show particularly strong depression at physiologically relevant rates of activity, which raises the question of how bushy cells transmit information when sound levels are high for a prolonged period. After rearing mice in constant, nondamaging noise, auditory nerve synapses changed from high to low P ᵣ, with a corresponding increase in the number of release sites, which increased spike fidelity during high activity. Neither quantal size nor average excitatory postsynaptic current changed. After returning to control conditions, P ᵣ recovered to high. These changes seem to reflect a homeostatic response to enhance fidelity.
Information processing in the brain requires reliable synaptic transmission. High reliability at specialized auditory nerve synapses in the cochlear nucleus results from many release sites ( N ), high probability of neurotransmitter release ( P ᵣ), and large quantal size ( Q ). However, high P ᵣ also causes auditory nerve synapses to depress strongly when activated at normal rates for a prolonged period, which reduces fidelity. We studied how synapses are influenced by prolonged activity by exposing mice to constant, nondamaging noise and found that auditory nerve synapses changed to facilitating, reflecting low P ᵣ. For mice returned to quiet, synapses recovered to normal depression, suggesting that these changes are a homeostatic response to activity. Two additional properties, Q and average excitatory postsynaptic current (EPSC) amplitude, were unaffected by noise rearing, suggesting that the number of release sites ( N ) must increase to compensate for decreased P ᵣ. These changes in N and P ᵣ were confirmed physiologically using the integration method. Furthermore, consistent with increased N , endbulbs in noise-reared animals had larger VGlut1-positive puncta, larger profiles in electron micrographs, and more release sites per profile. In current-clamp recordings, noise-reared BCs had greater spike fidelity even during high rates of synaptic activity. Thus, auditory nerve synapses regulate excitability through an activity-dependent, homeostatic mechanism, which could have major effects on all downstream processing. Our results also suggest that noise-exposed bushy cells would remain hyperexcitable for a period after returning to normal quiet conditions, which could have perceptual consequences.
The use of wearables facilitates data collection at a previously unobtainable scale, enabling the construction of complex predictive models with the potential to improve health. However, the highly ...personal nature of these data requires strong privacy protection against data breaches and the use of data in a way that users do not intend. One method to protect user privacy while taking advantage of sharing data across users is federated learning, a technique that allows a machine learning model to be trained using data from all users while only storing a user's data on that user's device. By keeping data on users' devices, federated learning protects users' private data from data leaks and breaches on the researcher's central server and provides users with more control over how and when their data are used. However, there are few rigorous studies on the effectiveness of federated learning in the mobile health (mHealth) domain.
We review federated learning and assess whether it can be useful in the mHealth field, especially for addressing common mHealth challenges such as privacy concerns and user heterogeneity. The aims of this study are to describe federated learning in an mHealth context, apply a simulation of federated learning to an mHealth data set, and compare the performance of federated learning with the performance of other predictive models.
We applied a simulation of federated learning to predict the affective state of 15 subjects using physiological and motion data collected from a chest-worn device for approximately 36 minutes. We compared the results from this federated model with those from a centralized or server model and with the results from training individual models for each subject.
In a 3-class classification problem using physiological and motion data to predict whether the subject was undertaking a neutral, amusing, or stressful task, the federated model achieved 92.8% accuracy on average, the server model achieved 93.2% accuracy on average, and the individual model achieved 90.2% accuracy on average.
Our findings support the potential for using federated learning in mHealth. The results showed that the federated model performed better than a model trained separately on each individual and nearly as well as the server model. As federated learning offers more privacy than a server model, it may be a valuable option for designing sensitive data collection methods.
In a departure from conventional chemical approaches, data-driven models of chemical reactions have recently been shown to be statistically successful using machine learning. These models, however, ...are largely black box in character and have not provided the kind of chemical insights that historically advanced the field of chemistry. To examine the knowledgebase of machine-learning modelswhat does the machine learnthis article deconstructs black-box machine-learning models of a diverse chemical reaction data set. Through experimentation with chemical representations and modeling techniques, the analysis provides insights into the nature of how statistical accuracy can arise, even when the model lacks informative physical principles. By peeling back the layers of these complicated models we arrive at a minimal, chemically intuitive model (and no machine learning involved). This model is based on systematic reaction-type classification and Evans–Polanyi relationships within reaction types which are easily visualized and interpreted. Through exploring this simple model, we gain deeper understanding of the data set and uncover a means for expert interactions to improve the model’s reliability.
Federated learning allows for the training of a model using data on multiple clients without the clients transmitting that raw data. However the standard method is to transmit model parameters (or ...updates), which for modern neural networks can be on the scale of millions of parameters, inflicting significant computational costs on the clients. We propose a method for federated learning where instead of transmitting a gradient update back to the server, we instead transmit a small amount of synthetic `data'. We describe the procedure and show some experimental results suggesting this procedure has potential, providing more than an order of magnitude reduction in communication costs with minimal model degradation.
Active learning seeks to build the best possible model with a budget of labelled data by sequentially selecting the next point to label. However the training set is no longer \textit{iid}, violating ...the conditions required by existing consistency results. Inspired by the success of Stone's Theorem we aim to regain consistency for weighted averaging estimators under active learning. Based on ideas in \citet{dasgupta2012consistency}, our approach is to enforce a small amount of random sampling by running an augmented version of the underlying active learning algorithm. We generalize Stone's Theorem in the noise free setting, proving consistency for well known classifiers such as \(k\)-NN, histogram and kernel estimators under conditions which mirror classical results. However in the presence of noise we can no longer deal with these estimators in a unified manner; for some satisfying this condition also guarantees sufficiency in the noisy case, while for others we can achieve near perfect inconsistency while this condition holds. Finally we provide conditions for consistency in the presence of noise, which give insight into why these estimators can behave so differently under the combination of noise and active learning.
Frame semantic parsing is an important component of task-oriented dialogue systems. Current models rely on a significant amount training data to successfully identify the intent and slots in the ...user's input utterance. This creates a significant barrier for adding new domains to virtual assistant capabilities, as creation of this data requires highly specialized NLP expertise. In this work we propose OpenFSP, a framework that allows for easy creation of new domains from a handful of simple labels that can be generated without specific NLP knowledge. Our approach relies on creating a small, but expressive, set of domain agnostic slot types that enables easy annotation of new domains. Given such annotation, a matching algorithm relying on sentence encoders predicts the intent and slots for domains defined by end-users. Extensive experiments on the TopV2 dataset shows that our model outperforms strong baselines in this simple labels setting.
Model compression is important in federated learning (FL) with large models to reduce communication cost. Prior works have been focusing on sparsification based compression that could desparately ...affect the global model accuracy. In this work, we propose a new scheme for upstream communication where instead of transmitting the model update, each client learns and transmits a light-weight synthetic dataset such that using it as the training data, the model performs similarly well on the real training data. The server will recover the local model update via the synthetic data and apply standard aggregation. We then provide a new algorithm FedSynth to learn the synthetic data locally. Empirically, we find our method is comparable/better than random masking baselines in all three common federated learning benchmark datasets.
Recent work has extended the theoretical analysis of boosting algorithms to multiclass problems and to online settings. However, the multiclass extension is in the batch setting and the online ...extensions only consider binary classification. We fill this gap in the literature by defining, and justifying, a weak learning condition for online multiclass boosting. This condition leads to an optimal boosting algorithm that requires the minimal number of weak learners to achieve a certain accuracy. Additionally, we propose an adaptive algorithm which is near optimal and enjoys an excellent performance on real data due to its adaptive property.
Improving the quality of Natural Language Understanding (NLU) models, and more specifically, task-oriented semantic parsing models, in production is a cumbersome task. In this work, we present a ...system called AutoNLU, which we designed to scale the NLU quality improvement process. It adds automation to three key steps: detection, attribution, and correction of model errors, i.e., bugs. We detected four times more failed tasks than with random sampling, finding that even a simple active learning sampling method on an uncalibrated model is surprisingly effective for this purpose. The AutoNLU tool empowered linguists to fix ten times more semantic parsing bugs than with prior manual processes, auto-correcting 65% of all identified bugs.
PDF
