AI-powered video analytics start-up CattleEye is in a field of its own having won the Irish leg of KPMG's Global Tech Innovator Competition. Belfast-based tech start-up CattleEye has won the top prize at KPMG's tech innovator competition, which saw entrants from all over Ireland. CattleEye uses AI-powered video analytics to keep an eye on cows. The start-up's CEO Terry Canning impressed the panel of judges, who also heard from eight other business people hoping to be crowned Ireland's top tech innovator. Canning's CattleEye will now progress to KPMG's Global Tech Innovator competition, which will be held at the Web Summit in Lisbon.

Style is an integral component of a sentence indicated by the choice of words a person makes. Different people have different ways of expressing themselves, however, they adjust their speaking and writing style to a social context, an audience, an interlocutor or the formality of an occasion. Text style transfer is defined as a task of adapting and/or changing the stylistic manner in which a sentence is written, while preserving the meaning of the original sentence. A systematic review of text style transfer methodologies using deep learning is presented in this paper. We point out the technological advances in deep neural networks that have been the driving force behind current successes in the fields of natural language understanding and generation. The review is structured around two key stages in the text style transfer process, namely, representation learning and sentence generation in a new style. The discussion highlights the commonalities and differences between proposed solutions as well as challenges and opportunities that are expected to direct and foster further research in the field.

COVID-19 has been a public health emergency of international concern since early 2020. Reliable forecasting is critical to diminish the impact of this disease. To date, a large number of different forecasting models have been proposed, mainly including statistical models, compartmental models, and deep learning models. However, due to various uncertain factors across different regions such as economics and government policy, no forecasting model appears to be the best for all scenarios. In this paper, we perform quantitative analysis of COVID-19 forecasting of confirmed cases and deaths across different regions in the United States with different forecasting horizons, and evaluate the relative impacts of the following three dimensions on the predictive performance (improvement and variation) through different evaluation metrics: model selection, hyperparameter tuning, and the length of time series required for training. We find that if a dimension brings about higher performance gains, if not well-tuned, it may also lead to harsher performance penalties. Furthermore, model selection is the dominant factor in determining the predictive performance. It is responsible for both the largest improvement and the largest variation in performance in all prediction tasks across different regions. While practitioners may perform more complicated time series analysis in practice, they should be able to achieve reasonable results if they have adequate insight into key decisions like model selection.

Variational inference for state space models (SSMs) is known to be hard in general. Recent works focus on deriving variational objectives for SSMs from unbiased sequential Monte Carlo estimators. We reveal that the marginal particle filter is obtained from sequential Monte Carlo by applying Rao-Blackwellization operations, which sacrifices the trajectory information for reduced variance and differentiability. We propose the variational marginal particle filter (VMPF), which is a differentiable and reparameterizable variational filtering objective for SSMs based on an unbiased estimator. We find that VMPF with biased gradients gives tighter bounds than previous objectives, and the unbiased reparameterization gradients are sometimes beneficial.

As an important problem of causal inference, we discuss the estimation of treatment effects (TEs) under unobserved confounding. Representing the confounder as a latent variable, we propose Intact-VAE, a new variant of variational autoencoder (VAE), motivated by the prognostic score that is sufficient for identifying TEs. Our VAE also naturally gives representation balanced for treatment groups, using its prior. Experiments on (semi-)synthetic datasets show state-of-the-art performance under diverse settings. Based on the identifiability of our model, further theoretical developments on identification and consistent estimation are also discussed. This paves the way towards principled causal effect estimation by deep neural networks.

"In a world more and more driven by AI models, Data Scientists cannot effectively ascertain on their own the costs associated with the unintended consequences of False Positives and False Negatives. Mitigating unintended consequences requires the collaboration across a diverse set of stakeholders in order to identify the metrics against which the AI Utility Function will seek to optimize." I've been fortunate enough to have had some interesting conversations since publishing that blog, especially with an organization who is championing data ethics and "Responsible AI" (love that term). As was so well covered in Cathy O'Neil's book "Weapons of Math Destruction", the biases built into many of the AI models that are being used to approve loans and mortgages, hire job applicants, and accept university admissions are yielding unintended consequences that severely impact both individuals and society. AI models only optimize against the metrics against which it has been programmed to optimize.

Training academy WeThinkCode female developers excelled at a gender-based-violence (GBV) hackathon held in Sandton, creating a tech solution targeting perpetrators of violence against women. The software developers were part of a four-member group going by the moniker "Winning Team", which picked up the top prize of the R30 000 that was up for grabs. The Winning Team, comprising Mmathabo Pule (25), Daisy Mangue (21), Keitumetse Bokaba (29) and Lulamile Mkhungela (30), emerged winners from a pool of 60 participants. Pule and Mangue are developers from WeThinkCode, which is on a mission to recruit more females to take up software development training. The 10th hackathon hosted by Empire Partner Foundation (EPF) focused on how SA can use innovation and tech to address and combat GBV by targeting the root cause: the perpetrators.

Nonnegative matrix factorization (NMF) has found many applications including topic modeling and document analysis. Hierarchical NMF (HNMF) variants are able to learn topics at various levels of granularity and illustrate their hierarchical relationship. Recently, nonnegative tensor factorization (NTF) methods have been applied in a similar fashion in order to handle data sets with complex, multi-modal structure. Hierarchical NTF (HNTF) methods have been proposed, however these methods do not naturally generalize their matrix-based counterparts. Here, we propose a new HNTF model which directly generalizes a HNMF model special case, and provide a supervised extension. We also provide a multiplicative updates training method for this model. Our experimental results show that this model more naturally illuminates the topic hierarchy than previous HNMF and HNTF methods.

Switching dynamical systems provide a powerful, interpretable modeling framework for inference in time-series data in, e.g., the natural sciences or engineering applications. Since many areas, such as biology or discrete-event systems, are naturally described in continuous time, we present a model based on an Markov jump process modulating a subordinated diffusion process. We provide the exact evolution equations for the prior and posterior marginal densities, the direct solutions of which are however computationally intractable. Therefore, we develop a new continuous-time variational inference algorithm, combining a Gaussian process approximation on the diffusion level with posterior inference for Markov jump processes. By minimizing the path-wise Kullback-Leibler divergence we obtain (i) Bayesian latent state estimates for arbitrary points on the real axis and (ii) point estimates of unknown system parameters, utilizing variational expectation maximization. We extensively evaluate our algorithm under the model assumption and for real-world examples.

This is a Women in AI Podcast transcript, for this interview we have Wendy Gonzalez, CEO at Sama, speaking with us about high-quality data training and what she's getting up to in her current role. We hope you enjoy the episode. Listen to the podcast here. So today I'm joined by Wendy Gonzalez on our Women in AI podcast episode, who is the Interim CEO of Sama, and I'm really excited to speak to her today. Hi, Wendy, how are you?