This paper proves the concept that it is feasible to accurately recognize specific human mobility shared patterns, based solely on the connection logs between portable devices and WiFi Access Points (APs), while preserving user's privacy. We gathered data from the Eduroam WiFi network of Polytechnique Montreal, making omission of device tracking or physical layer data. The behaviors we chose to detect were the movements associated to the end of an academic class, and the patterns related to the small break periods between classes. Stringent conditions were self-imposed in our experiments. The data is known to have errors noise, and be susceptible to information loss. No countermeasures were adopted to mitigate any of these issues. Data pre-processing consists of basic statistics that were used in aggregating the data in time intervals. We obtained accuracy values of 93.7 % and 83.3 % (via Bagged Trees) when recognizing behaviour patterns of breaks between classes and end-of-classes, respectively.

Floating Content (FC) is a communication paradigm for the local dissemination of contextualized information through D2D connectivity, in a way which minimizes the use of resources while achieving some specified performance target. Existing approaches to FC dimensioning are based on unrealistic system assumptions that make them, highly inaccurate and overly conservative when applied in realistic settings. In this paper, we present a first step towards the development of a cognitive approach to efficient dynamic management of FC. We propose a deep learning strategy for FC dimensioning, which exploits a Convolutional Neural Network(CNN) to efficiently modulate over time the resources employed by FC in a QoS-aware manner. Numerical evaluations show that our approach achieves a maximum rejection rate of3%, and resource savings of 37.5% with respect to the benchmark strategy

Abstract--This paper introduces new attention-based convolutional neural networks for selecting bands from hyperspectral images. The proposed approach reuses convolutional activations at different depths, identifying the most informative regions of the spectrum with the help of gating mechanisms. Our attention techniques are modular and easy to implement, and they can be seamlessly trained end-to-end using gradient descent. Our rigorous experiments showed that deep models equipped with the attention mechanism deliver high-quality classification, and repeatedly identify significant bands in the training data, permitting the creation of refined and extremely compact sets that retain the most meaningful features. Hyperspectral data's high dimensionality is an important challenge towards its accurate segmentation, efficient analysis, transfer and storage.

Sepsis is a life-threatening disease and one of the major causes of death in hospitals. Imaging of microcirculatory dysfunction is a promising approach for automated diagnosis of sepsis. We report a machine learning classifier capable of distinguishing non-septic and septic images from dark field microcirculation videos of patients. The classifier achieves an accuracy of 89.45%. The area under the receiver operating characteristics of the classifier was 0.92, the precision was 0.92 and the recall was 0.84. Codes representing the learned feature space of trained classifier were visualized using t-SNE embedding and were separable and distinguished between images from critically ill and non-septic patients. Using an unsupervised convolutional autoencoder, independent of the clinical diagnosis, we also report clustering of learned features from a compressed representation associated with healthy images and those with microcirculatory dysfunction. The feature space used by our trained classifier to distinguish between images from septic and non-septic patients has potential diagnostic application.

We introduce a novel method that enables parameter-efficient transfer and multitask learning. The basic approach is to allow a model patch - a small set of parameters - to specialize to each task, instead of fine-tuning the last layer or the entire network. For instance, we show that learning a set of scales and biases allows a network to learn a completely different embedding that could be used for different tasks (such as converting an SSD detection model into a 1000-class classification model while reusing 98% of parameters of the feature extractor). Similarly, we show that re-learning the existing low-parameter layers (such as depth-wise convolutions) also improves accuracy significantly. Our approach allows both simultaneous (multi-task) learning as well as sequential transfer learning wherein we adapt pretrained networks to solve new problems. For multi-task learning, despite using much fewer parameters than traditional logits-only fine-tuning, we match single-task-based performance.

We present a learning-based approach to computing solutions for certain NP-hard problems. Our approach combines deep learning techniques with useful algorithmic elements from classic heuristics. The central component is a graph convolutional network that is trained to estimate the likelihood, for each vertex in a graph, of whether this vertex is part of the optimal solution. The network is designed and trained to synthesize a diverse set of solutions, which enables rapid exploration of the solution space via tree search. The presented approach is evaluated on four canonical NP-hard problems and five datasets, which include benchmark satisfiability problems and real social network graphs with up to a hundred thousand nodes. Experimental results demonstrate that the presented approach substantially outperforms recent deep learning work, and performs on par with highly optimized state-of-the-art heuristic solvers for some NP-hard problems. Experiments indicate that our approach generalizes across datasets, and scales to graphs that are orders of magnitude larger than those used during training.

It is by now well-known that small adversarial perturbations can induce classification errors in deep neural networks. In this paper, we make the case that a systematic exploitation of sparsity is key to defending against such attacks, and that a "locally linear" model for neural networks can be used to develop a theoretical foundation for crafting attacks and defenses. We consider two defenses. The first is a sparsifying front end, which attenuates the impact of the attack by a factor of roughly $K/N$ where $N$ is the data dimension and $K$ is the sparsity level. The second is sparsification of network weights, which attenuates the worst-case growth of an attack as it flows up the network. We also devise attacks based on the locally linear model that outperform the well-known FGSM attack. We provide experimental results for the MNIST and Fashion-MNIST datasets, showing the efficacy of the proposed sparsity-based defenses.

Disease progression models are instrumental in predicting individual-level health trajectories and understanding disease dynamics. Existing models are capable of providing either accurate predictions of patients' prognoses or clinically interpretable representations of disease pathophysiology, but not both. In this paper, we develop the phased attentive state space (PASS) model of disease progression, a deep probabilistic model that captures complex representations for disease progression while maintaining clinical interpretability. Unlike Markovian state space models which assume memoryless dynamics, PASS uses an attention mechanism to induce "memoryful" state transitions, whereby repeatedly updated attention weights are used to focus on past state realizations that best predict future states. This gives rise to complex, non-stationary state dynamics that remain interpretable through the generated attention weights, which designate the relationships between the realized state variables for individual patients. PASS uses phased LSTM units (with time gates controlled by parametrized oscillations) to generate the attention weights in continuous time, which enables handling irregularly-sampled and potentially missing medical observations. Experiments on data from a real-world cohort of patients show that PASS successfully balances the tradeoff between accuracy and interpretability: it demonstrates superior predictive accuracy and learns insightful individual-level representations of disease progression.

This paper concerns automated vehicles negotiating with other vehicles, typically human driven, in crossings with the goal to find a decision algorithm by learning typical behaviors of other vehicles. The vehicle observes distance and speed of vehicles on the intersecting road and use a policy that adapts its speed along its pre-defined trajectory to pass the crossing efficiently. Deep Q-learning is used on simulated traffic with different predefined driver behaviors and intentions. The results show a policy that is able to cross the intersection avoiding collision with other vehicles 98% of the time, while at the same time not being too passive. Moreover, inferring information over time is important to distinguish between different intentions and is shown by comparing the collision rate between a Deep Recurrent Q-Network at 0.85% and a Deep Q-learning at 1.75%.

Despite recent developments, deploying deep neural networks on resource constrained general purpose hardware remains a significant challenge. There has been much work in developing methods for reshaping neural networks, usually with a focus on minimising total parameter count. These methods are typically developed in a hardware-agnostic manner and do not exploit hardware behaviour. In this paper we propose a new approach, Hardware Aware Knowledge Distillation (HAKD) which uses empirical observations of hardware behaviour to design efficient student networks which are then trained with knowledge distillation. This allows the trade-off between accuracy and performance to be managed explicitly. We have applied this approach across three platforms and evaluated it on two networks, MobileNet and DenseNet, on CIFAR-10. We show that HAKD outperforms Deep Compression and Fisher pruning in terms of size, accuracy and performance.