Even though model predictive control (MPC) is currently the main algorithm for insulin control in the artificial pancreas (AP), it usually requires complex online optimizations, which are infeasible for resource-constrained medical devices. MPC also typically relies on state estimation, an error-prone process. In this paper, we introduce a novel approach to AP control that uses Imitation Learning to synthesize neural-network insulin policies from MPC-computed demonstrations. Such policies are computationally efficient and, by instrumenting MPC at training time with full state information, they can directly map measurements into optimal therapy decisions, thus bypassing state estimation. We apply Bayesian inference via Monte Carlo Dropout to learn policies, which allows us to quantify prediction uncertainty and thereby derive safer therapy decisions. We show that our control policies trained under a specific patient model readily generalize (in terms of model parameters and disturbance distributions) to patient cohorts, consistently outperforming traditional MPC with state estimation.

Despite fluorescent cell-labelling being widely employed in biomedical studies, some of its drawbacks are inevitable, with unsuitable fluorescent probes or probes inducing a functional change being the main limitations. Consequently, the demand for and development of label-free methodologies to classify cells is strong and its impact on precision medicine is relevant. Towards this end, high-throughput techniques for cell mechanical phenotyping have been proposed to get a multidimensional biophysical characterization of single cells. With this motivation, our goal here is to investigate the extent to which an unsupervised machine learning methodology, which is applied exclusively on morpho-rheological markers obtained by real-time deformability and fluorescence cytometry (RT-FDC), can address the difficult task of providing label-free discrimination of reticulocytes from mature red blood cells. We focused on this problem, since the characterization of reticulocytes (their percentage and cellular features) in the blood is vital in multiple human disease conditions, especially bone-marrow disorders such as anemia and leukemia. Our approach reports promising label-free results in the classification of reticulocytes from mature red blood cells, and it represents a step forward in the development of high-throughput morpho-rheological-based methodologies for the computational categorization of single cells. Besides, our methodology can be an alternative but also a complementary method to integrate with existing cell-labelling techniques.

We study a distributed decision-making problem in which multiple agents face the same multi-armed bandit (MAB), and each agent makes sequential choices among arms to maximize its own individual reward. The agents cooperate by sharing their estimates over a fixed communication graph. We consider an unconstrained reward model in which two or more agents can choose the same arm and collect independent rewards. And we consider a constrained reward model in which agents that choose the same arm at the same time receive no reward. We design a dynamic, consensus-based, distributed estimation algorithm for cooperative estimation of mean rewards at each arm. We leverage the estimates from this algorithm to develop two distributed algorithms: coop-UCB2 and coop-UCB2-selective-learning, for the unconstrained and constrained reward models, respectively. We show that both algorithms achieve group performance close to the performance of a centralized fusion center. Further, we investigate the influence of the communication graph structure on performance. We propose a novel graph explore-exploit index that predicts the relative performance of groups in terms of the communication graph, and we propose a novel nodal explore-exploit centrality index that predicts the relative performance of agents in terms of the agent locations in the communication graph.

Class selectivity, typically defined as how different a neuron's responses are across different classes of stimuli or data samples, is a common metric used to interpret the function of individual neurons in biological and artificial neural networks. However, it remains an open question whether it is necessary and/or sufficient for deep neural networks (DNNs) to learn class selectivity in individual units. In order to investigate the causal impact of class selectivity on network function, we directly regularize for or against class selectivity. Using this regularizer, we were able to reduce mean class selectivity across units in convolutional neural networks by a factor of 2.5 with no impact on test accuracy, and reduce it nearly to zero with only a small ($\sim$2%) change in test accuracy. In contrast, increasing class selectivity beyond the levels naturally learned during training had rapid and disastrous effects on test accuracy. These results indicate that class selectivity in individual units is neither neither sufficient nor strictly necessary for DNN performance, and more generally encourage caution when focusing on the properties of single units as representative of the mechanisms by which DNNs function.

We describe a new approach to estimating relative risks in time-to-event prediction problems with censored data in a fully parametric manner. Our approach does not require making strong assumptions of constant baseline hazard of the underlying survival distribution, as required by the Cox-proportional hazard model. By jointly learning deep nonlinear representations of the input covariates, we demonstrate the benefits of our approach when used to estimate survival risks through extensive experimentation on multiple real world datasets with different levels of censoring. We further demonstrate advantages of our model in the competing risks scenario. To the best of our knowledge, this is the first work involving fully parametric estimation of survival times with competing risks in the presence of censoring.

Electronic health records (EHR) consist of longitudinal clinical observations portrayed with sparsity, irregularity, and high-dimensionality, which become major obstacles in drawing reliable downstream clinical outcomes. Although there exist great numbers of imputation methods to tackle these issues, most of them ignore correlated features, temporal dynamics and entirely set aside the uncertainty. Since the missing value estimates involve the risk of being inaccurate, it is appropriate for the method to handle the less certain information differently than the reliable data. In that regard, we can use the uncertainties in estimating the missing values as the fidelity score to be further utilized to alleviate the risk of biased missing value estimates. In this work, we propose a novel variational-recurrent imputation network, which unifies an imputation and a prediction network by taking into account the correlated features, temporal dynamics, as well as the uncertainty. Specifically, we leverage the deep generative model in the imputation, which is based on the distribution among variables, and a recurrent imputation network to exploit the temporal relations, in conjunction with utilization of the uncertainty. We validated the effectiveness of our proposed model on two publicly available real-world EHR datasets: PhysioNet Challenge 2012 and MIMIC-III, and compared the results with other competing state-of-the-art methods in the literature.

Deep neural networks have been widely applied as an effective approach to handle complex and practical problems. However, one of the most fundamental open problems is the lack of formal methods to analyze the safety of their behaviors. To address this challenge, we propose a parallelizable technique to compute exact reachable sets of a neural network to an input set. Our method currently focuses on feed-forward neural networks with ReLU activation functions. One of the primary challenges for polytope-based approaches is identifying the intersection between intermediate polytopes and hyperplanes from neurons. In this regard, we present a new approach to construct the polytopes with the face lattice, a complete combinatorial structure. The correctness and performance of our methodology are evaluated by verifying the safety of ACAS Xu networks and other benchmarks. Compared to state-of-the-art methods such as Reluplex, Marabou, and NNV, our approach exhibits a significantly higher efficiency. Additionally, our approach is capable of constructing the complete input set given an output set, so that any input that leads to safety violation can be tracked.

The intuitive collaboration of humans and intelligent robots (embodied AI) in the real-world is an essential objective for many desirable applications of robotics. Whilst there is much research regarding explicit communication, we focus on how humans and robots interact implicitly, on motor adaptation level. We present a real-world setup of a human-robot collaborative maze game, designed to be non-trivial and only solvable through collaboration, by limiting the actions to rotations of two orthogonal axes, and assigning each axes to one player. This results in neither the human nor the agent being able to solve the game on their own. We use a state-of-the-art reinforcement learning algorithm for the robotic agent, and achieve results within 30 minutes of real-world play, without any type of pre-training. We then use this system to perform systematic experiments on human/agent behaviour and adaptation when co-learning a policy for the collaborative game. We present results on how co-policy learning occurs over time between the human and the robotic agent resulting in each participant's agent serving as a representation of how they would play the game. This allows us to relate a person's success when playing with different agents than their own, by comparing the policy of the agent with that of their own agent.

Iterate averaging has a rich history in optimisation, but has only very recently been popularised in deep learning. We investigate its effects in a deep learning context, and argue that previous explanations on its efficacy, which place a high importance on the local geometry (flatness vs sharpness) of final solutions, are not necessarily relevant. We instead argue that the robustness of iterate averaging towards the typically very high estimation noise in deep learning and the various regularisation effects averaging exert, are the key reasons for the performance gain, indeed this effect is made even more prominent due to the over-parameterisation of modern networks. Inspired by this, we propose Gadam, which combines Adam with iterate averaging to address one of key problems of adaptive optimisers that they often generalise worse. Without compromising adaptivity and with minimal additional computational burden, we show that Gadam (and its variant GadamX) achieve a generalisation performance that is consistently superior to tuned SGD and is even on par or better compared to SGD with iterate averaging on various image classification (CIFAR 10/100 and ImageNet 32$\times$32) and language tasks (PTB).

We consider robust optimization problems, where the goal is to optimize an unknown objective function against the worst-case realization of an uncertain parameter. For this setting, we design a novel sample-efficient algorithm GP-MRO, which sequentially learns about the unknown objective from noisy point evaluations. GP-MRO seeks to discover a robust and randomized mixed strategy, that maximizes the worst-case expected objective value. To achieve this, it combines techniques from online learning with nonparametric confidence bounds from Gaussian processes. Our theoretical results characterize the number of samples required by GP-MRO to discover a robust near-optimal mixed strategy for different GP kernels of interest. We experimentally demonstrate the performance of our algorithm on synthetic datasets and on human-assisted trajectory planning tasks for autonomous vehicles. In our simulations, we show that robust deterministic strategies can be overly conservative, while the mixed strategies found by GP-MRO significantly improve the overall performance.