Many natural language processing (NLP) tasks make use of massively pre-trained language models, which are computationally expensive. However, access to high computational resources added to the issue of data scarcity of African languages constitutes a real barrier to research experiments on these languages. In this work, we explore the applicability of low-compute approaches such as language adapters in the context of this low-resource double-bind. We intend to answer the following question: do language adapters allow those who are doubly bound by data and compute to practically build useful models? Through fine-tuning experiments on African languages, we evaluate their effectiveness as cost-effective approaches to low-resource African NLP. Using solely free compute resources, our results show that language adapters achieve comparable performances to massive pre-trained language models which are heavy on computational resources. This opens the door to further experimentation and exploration on full-extent of language adapters capacities.

In this context, defining and analysing their mobility is particularly important. A mobility model describes the behaviour of an entity considering its capacities, possible moves and speed. The mobility models are described either analytically at the individual level, or by the interactions between the parts of the system (between UAVs, UAVs and planes, UAVs and points to survey, etc.). The resulting behaviours described with these simple rules can induce the emergence of a global intelligent behaviour. Inversely, from the resulting behaviour of such a swarm, these initial simple rules are hard to discover.

Pre-trained large language models have recently achieved ground-breaking performance in a wide variety of language understanding tasks. However, the same model can not be applied to multimodal behavior understanding tasks (e.g., video sentiment/humor detection) unless non-verbal features (e.g., acoustic and visual) can be integrated with language. Jointly modeling multiple modalities significantly increases the model complexity, and makes the training process data-hungry. While an enormous amount of text data is available via the web, collecting large-scale multimodal behavioral video datasets is extremely expensive, both in terms of time and money. In this paper, we investigate whether large language models alone can successfully incorporate non-verbal information when they are presented in textual form. We present a way to convert the acoustic and visual information into corresponding textual descriptions and concatenate them with the spoken text. We feed this augmented input to a pre-trained BERT model and fine-tune it on three downstream multimodal tasks: sentiment, humor, and sarcasm detection. Our approach, TextMI, significantly reduces model complexity, adds interpretability to the model's decision, and can be applied for a diverse set of tasks while achieving superior (multimodal sarcasm detection) or near SOTA (multimodal sentiment analysis and multimodal humor detection) performance. We propose TextMI as a general, competitive baseline for multimodal behavioral analysis tasks, particularly in a low-resource setting.

There is no doubt that GPT-4, the latest iteration of the artificial-intelligence engine created by the company OpenAI, is innovative and cool. It can create a poem in the style of Basho, spell out the chord progression and time signature for a simple tune, and provide a seven-step recipe for a peanut-butter-and-jelly sandwich. When I asked it to write a musical about a narcissistic politician who holds the fate of the world in his hands, it delivered a story in two acts, with a protagonist named Alex Sterling who "navigates a maze of power, manipulation, and the consequences of his decisions," as he sings "Narcissus in the Mirror," "The Price of Power," and about a dozen other invented songs. Those songs appear to have been created out of thin air; certainly, no human conceived them. Still, Alex's story, which "explores themes of self-discovery, redemption, and the responsibility of leadership," is quite familiar.

OUTsurance has been propelling the South African insurance industry forward for the last 25 years. As leaders in the field, we're always looking for innovative ways to create digitally-advanced solutions, without losing sight of our human values. Our continued success can be attributed to OUTstanding employees who set the bar high with their energy and expertise. If you're keen to grow your career in a vibrant environment with lots of friendly'gees', this could be the career opportunity you've been looking for. Do you live and breathe all things data related?

Kuda is a money app for Africans on a mission to make financial services accessible, affordable and rewarding for every African on the planet. We're a tribe of passionate and diverse people who dreamed of building an inclusive money app that Africans would love so it's only right that we ended up with the name'Kuda' which means'love' in Shona, a language spoken in the southern part of Africa. We're giving Africans around the world a better alternative to traditional finance by delivering money transfers, smart budgeting and instant access to credit through digital devices. We've raised over $90 million from some of the world's most respected institutional investors, and we're rolling out our game-changing services globally from our offices in Nigeria, South Africa, and the UK. Role Overview: This is a BI Analyst role dedicated to operational reporting and analytics.

As black-box models increasingly power high-stakes applications, a variety of data-driven explanation methods have been introduced. Meanwhile, machine learning models are constantly challenged by distributional shifts. A question naturally arises: Are data-driven explanations robust against out-of-distribution data? Our empirical results show that even though predict correctly, the model might still yield unreliable explanations under distributional shifts. How to develop robust explanations against out-of-distribution data? To address this problem, we propose an end-to-end model-agnostic learning framework Distributionally Robust Explanations (DRE). The key idea is, inspired by self-supervised learning, to fully utilizes the inter-distribution information to provide supervisory signals for the learning of explanations without human annotation. Can robust explanations benefit the model's generalization capability? We conduct extensive experiments on a wide range of tasks and data types, including classification and regression on image and scientific tabular data. Our results demonstrate that the proposed method significantly improves the model's performance in terms of explanation and prediction robustness against distributional shifts.

Neural networks have revolutionized many aspects of society but in the era of huge models with billions of parameters, optimizing and deploying them for commercial applications can require significant computational and financial resources. To address these challenges, we introduce the Tetra-AML toolbox, which automates neural architecture search and hyperparameter optimization via a custom-developed black-box Tensor train Optimization algorithm, TetraOpt. The toolbox also provides model compression through quantization and pruning, augmented by compression using tensor networks. Here, we analyze a unified benchmark for optimizing neural networks in computer vision tasks and show the superior performance of our approach compared to Bayesian optimization on the CIFAR-10 dataset. We also demonstrate the compression of ResNet-18 neural networks, where we use 14.5 times less memory while losing just 3.2% of accuracy. The presented framework is generic, not limited by computer vision problems, supports hardware acceleration (such as with GPUs and TPUs) and can be further extended to quantum hardware and to hybrid quantum machine learning models.

This article proposes a partial solution to these three issues, in the form of controlled generation of synthetic text with large language models. I provide a conceptual overview of text generation, guidance on when researchers should prefer different techniques for generating synthetic text, a discussion of ethics, and a simple technique for improving the quality of synthetic text. I demonstrate the usefulness of synthetic text with three applications: generating synthetic tweets describing the fighting in Ukraine, synthetic news articles describing specified political events for training an event detection system, and a multilingual corpus of populist manifesto statements for training a sentence-level populism classifier.

The literature on provable robustness in machine learning has primarily focused on static prediction problems, such as image classification, in which input samples are assumed to be independent and model performance is measured as an expectation over the input distribution. Robustness certificates are derived for individual input instances with the assumption that the model is evaluated on each instance separately. However, in many deep learning applications such as online content recommendation and stock market analysis, models use historical data to make predictions. Robustness certificates based on the assumption of independent input samples are not directly applicable in such scenarios. In this work, we focus on the provable robustness of machine learning models in the context of data streams, where inputs are presented as a sequence of potentially correlated items. We derive robustness certificates for models that use a fixed-size sliding window over the input stream. Our guarantees hold for the average model performance across the entire stream and are independent of stream size, making them suitable for large data streams. We perform experiments on speech detection and human activity recognition tasks and show that our certificates can produce meaningful performance guarantees against adversarial perturbations.