The vast majority of machine learning algorithms involve two different sets of parameters: the training parameters and the meta-parameters (also known as hyperparameters). While the training parameters are learned during the training phase, the values of the hyperparameters have to be specified before the learning phase. For instance, the hyperparameters of neural networks typically specify the architecture of the network (number and type of layers, number and type of nodes, etc). Determining the optimal combination of hyperparameter values leading to the best generalization performance can be done through repeated training and evaluation sessions, trying different combinations of hyperparameter values. We call each training evaluation process for one combination of hyperparameter values a trial. Each trial is computationally expensive, since it involves retraining the model.

Stress is a growing concern in modern society adversely impacting the wider population more than ever before. The accurate inference of stress may result in the possibility for personalised interventions. However, individual differences between people limits the generalisability of machine learning models to infer emotions as people's physiology when experiencing the same emotions widely varies. In addition, it is time consuming and extremely challenging to collect large datasets of individuals' emotions as it relies on users labelling sensor data in real-time for extended periods. We propose the development of a personalised, cross-domain 1D CNN by utilising transfer learning from an initial base model trained using data from 20 participants completing a controlled stressor experiment. By utilising physiological sensors (HR, HRV EDA) embedded within edge computing interfaces that additionally contain a labelling technique, it is possible to collect a small real-world personal dataset that can be used for on-device transfer learning to improve model personalisation and cross-domain performance.

Rice is the second most important cereal crop worldwide, and the first in terms of number of people who depend on it as a major staple food. Rice blast disease is the most important biotic constraint of rice cultivation causing each year millions of dollars of losses. Despite the efforts for breeding new resistant varieties, agricultural practices and chemical control are still the most important methods for disease management. Thus, rice blast forecasting is a primary tool to support rice growers in controlling the disease. In this study, we compared four models for predicting rice blast disease, two operational process-based models (Yoshino and WARM) and two approaches based on machine learning algorithms (M5Rules and RNN), the former inducing a rule-based model and the latter building a neural network. In situ telemetry is important to obtain quality in-field data for predictive models and this was a key aspect of the RICE-GUARD project on which this study is based. According to the authors, this is the first time process-based and machine learning modelling approaches for supporting plant disease management are compared.

Gaussian processes provide a probabilistic framework for quantifying uncertainty of prediction and have been adopted in many applications in Statistics and Bayesian optimization. Unfortunately, they are hard to scale to large datasets as they necessitate inverting matrices whose size is linear in the number of observations. Moreover, they necessitate an a priori chosen functional form for their kernels with predetermined features. Our contribution is a framework that addresses both challenges. We use deep neural networks for automatic feature extraction, combined with explicit functional forms for the eigenspectrum of Gaussian processes with Gaussian kernels, to derive a Gaussian process inference and prediction framework whose complexity scales linearly in the number of observations and which accommodates automatic feature extraction. On a series of datasets, our method outperforms state of the art scalable Gaussian process approximations.

We propose a novel framework for integrating Hawkes processes with multi-armed bandit algorithms to solve spatio-temporal event forecasting and detection problems when data may be undersampled or spatially biased. In particular, we introduce an upper confidence bound algorithm using Bayesian spatial Hawkes process estimation for balancing the tradeoff between exploiting geographic regions where data has been collected and exploring geographic regions where data is unobserved. We first validate our model using simulated data and then apply it to the problem of disaster search and rescue using calls for service data from hurricane Harvey in 2017. Our model outperforms the state of the art baseline spatial MAB algorithms in terms of cumulative reward and several other ranking evaluation metrics.

This work is a trial in which we propose SIR model and machine learning tools to analyze the coronavirus pandemic in the real world. Based on the public data from \cite{datahub}, we estimate main key pandemic parameters and make predictions on the inflection point and possible ending time for the real world and specifically for Senegal. The coronavirus disease 2019, by World Health Organization, rapidly spread out in the whole China and then in the whole world. Under optimistic estimation, the pandemic in some countries will end soon, while for most part of countries in the world (US, Italy, etc.), the hit of anti-pandemic will be no later than the end of April.

We introduce tramp, standing for TRee Approximate Message Passing, a python package for compositional inference in high-dimensional tree-structured models. The package provides an unifying framework to study several approximate message passing algorithms previously derived for a variety of machine learning tasks such as generalized linear models, inference in multi-layer networks, matrix factorization, and reconstruction using non-separable penalties. For some models, the asymptotic performance of the algorithm can be theoretically predicted by the state evolution, and the measurements entropy estimated by the free entropy formalism. The implementation is modular by design: each module, which implements a factor, can be composed at will with other modules to solve complex inference tasks. The user only needs to declare the factor graph of the model: the inference algorithm, state evolution and entropy estimation are fully automated.

Variational autoencoder (VAE) is a widely used generative model for unsupervised learning of vector data. The learning capacity of VAE is often limited by \textit{over-pruning} - a phenomenon that prevents many of the latent dimensions from learning any useful information about the input data. Variational graph autoencoder (VGAE) extends VAE for unsupervised learning of graph-structured data. Being an extension of VAE model, VGAE, also suffers from over-pruning in principal. In this paper we look at over-pruning in VGAE and observe that the generative capacity of VGAE is limited because of the way VGAE deals with this issue. We then propose epitomic variational graph autoencoder (EVGAE), a generative variational framework for graph datasets to overcome over-pruning. We show through experiments that the resulting model has a better generative ability and also achieves better scores in graph analysis related tasks.

Although Shannon theory states that it is asymptotically optimal to separate the source and channel coding as two independent processes, in many practical communication scenarios this decomposition is limited by the finite bit-length and computational power for decoding. Recently, neural joint source-channel coding (NECST) is proposed to sidestep this problem. While it leverages the advancements of amortized inference and deep learning to improve the encoding and decoding process, it still cannot always achieve compelling results in terms of compression and error correction performance due to the limited robustness of its learned coding networks. In this paper, motivated by the inherent connections between neural joint source-channel coding and discrete representation learning, we propose a novel regularization method called Infomax Adversarial-Bit-Flip (IABF) to improve the stability and robustness of the neural joint source-channel coding scheme. More specifically, on the encoder side, we propose to explicitly maximize the mutual information between the codeword and data; while on the decoder side, the amortized reconstruction is regularized within an adversarial framework. Extensive experiments conducted on various real-world datasets evidence that our IABF can achieve state-of-the-art performances on both compression and error correction benchmarks and outperform the baselines by a significant margin.

Most algorithms for solving optimization problems or finding saddle points of convex-concave functions are fixed point algorithms. In this work we consider the generic problem of finding a fixed point of an average of operators, or an approximation thereof, in a distributed setting. Our work is motivated by the needs of federated learning. In this context, each local operator models the computations done locally on a mobile device. We investigate two strategies to achieve such a consensus: one based on a fixed number of local steps, and the other based on randomized computations. In both cases, the goal is to limit communication of the locally-computed variables, which is often the bottleneck in distributed frameworks. We perform convergence analysis of both methods and conduct a number of experiments highlighting the benefits of our approach.