The ACII Affective Vocal Bursts Workshop & Competition is focused on understanding multiple affective dimensions of vocal bursts: laughs, gasps, cries, screams, and many other non-linguistic vocalizations central to the expression of emotion and to human communication more generally. This year's competition comprises four tracks using a large-scale and in-the-wild dataset of 59,299 vocalizations from 1,702 speakers. The first, the A-VB-High task, requires competition participants to perform a multi-label regression on a novel model for emotion, utilizing ten classes of richly annotated emotional expression intensities, including; Awe, Fear, and Surprise. The second, the A-VB-Two task, utilizes the more conventional 2-dimensional model for emotion, arousal, and valence. The third, the A-VB-Culture task, requires participants to explore the cultural aspects of the dataset, training native-country dependent models. Finally, for the fourth task, A-VB-Type, participants should recognize the type of vocal burst (e.g., laughter, cry, grunt) as an 8-class classification. This paper describes the four tracks and baseline systems, which use state-of-the-art machine learning methods. The baseline performance for each track is obtained by utilizing an end-to-end deep learning model and is as follows: for A-VB-High, a mean (over the 10-dimensions) Concordance Correlation Coefficient (CCC) of 0.5687 CCC is obtained; for A-VB-Two, a mean (over the 2-dimensions) CCC of 0.5084 is obtained; for A-VB-Culture, a mean CCC from the four cultures of 0.4401 is obtained; and for A-VB-Type, the baseline Unweighted Average Recall (UAR) from the 8-classes is 0.4172 UAR.

The ability to identify influential training examples enables us to debug training data and explain model behavior. Existing techniques to do so are based on the flow of training data influence through the model parameters. For large models in NLP applications, it is often computationally infeasible to study this flow through all model parameters, therefore techniques usually pick the last layer of weights. However, we observe that since the activation connected to the last layer of weights contains "shared logic", the data influenced calculated via the last layer weights prone to a ``cancellation effect'', where the data influence of different examples have large magnitude that contradicts each other. The cancellation effect lowers the discriminative power of the influence score, and deleting influential examples according to this measure often does not change the model's behavior by much. To mitigate this, we propose a technique called TracIn-WE that modifies a method called TracIn to operate on the word embedding layer instead of the last layer, where the cancellation effect is less severe. One potential concern is that influence based on the word embedding layer may not encode sufficient high level information. However, we find that gradients (unlike embeddings) do not suffer from this, possibly because they chain through higher layers. We show that TracIn-WE significantly outperforms other data influence methods applied on the last layer significantly on the case deletion evaluation on three language classification tasks for different models. In addition, TracIn-WE can produce scores not just at the level of the overall training input, but also at the level of words within the training input, a further aid in debugging.

We study the problem of generating a training-free task-dependent visual classifier from text descriptions without visual samples. This Text-to-Model (T2M) problem is closely related to zero-shot learning, but unlike previous work, a T2M model infers a model tailored to a task, taking into account all classes in the task. We analyze the symmetries of T2M, and characterize the equivariance and invariance properties of corresponding models. In light of these properties we design an architecture based on hypernetworks that given a set of new class descriptions predicts the weights for an object recognition model which classifies images from those zero-shot classes. We demonstrate the benefits of our approach compared to zero-shot learning from text descriptions in image and point-cloud classification using various types of text descriptions: From single words to rich text descriptions. The dominant paradigm for obtaining predictive models in machine learning is inductive training, often using massive labeled datasets. In contrast, people employ other techniques to obtain predictive models. Specifically, they create task-specific discriminative models based on language instructions, such as "separate soft toys from hard ones" or "collect the furry toy animals" (Markman, 1990). This contrast between machine and human learning is striking, but until now, teaching machines to obtain task-specific discriminative models from natural language descriptions has been limited. Language-based classification has been studied for the closely related, yet different, task of zeroshot learning from text or attributes (ZSL) (Frome et al., 2013; Lampert et al., 2013). Then, images of an unseen concept can be categorized by finding the class whose descriptor is closest to the image in the shared space. The issue is that in this family of approaches the learned representation (and the kNN classifier that it induces) are fixed after training, and are not tuned to a classification task given at inference time.

Transformer-based pre-trained language models (PLMs) mostly suffer from excessive overhead despite their advanced capacity. For resource-constrained devices, there is an urgent need for a spatially and temporally efficient model which retains the major capacity of PLMs. However, existing statically compressed models are unaware of the diverse complexities between input instances, potentially resulting in redundancy and inadequacy for simple and complex inputs. Also, miniature models with early exiting encounter challenges in the trade-off between making predictions and serving the deeper layers. Motivated by such considerations, we propose a collaborative optimization for PLMs that integrates static model compression and dynamic inference acceleration. Specifically, the PLM is slenderized in width while the depth remains intact, complementing layer-wise early exiting to speed up inference dynamically. To address the trade-off of early exiting, we propose a joint training approach that calibrates slenderization and preserves contributive structures to each exit instead of only the final layer. Experiments are conducted on GLUE benchmark and the results verify the Pareto optimality of our approach at high compression and acceleration rate with 1/8 parameters and 1/19 FLOPs of BERT.

Single-index models are a class of functions given by an unknown univariate ``link'' function applied to an unknown one-dimensional projection of the input. These models are particularly relevant in high dimension, when the data might present low-dimensional structure that learning algorithms should adapt to. While several statistical aspects of this model, such as the sample complexity of recovering the relevant (one-dimensional) subspace, are well-understood, they rely on tailored algorithms that exploit the specific structure of the target function. In this work, we introduce a natural class of shallow neural networks and study its ability to learn single-index models via gradient flow. More precisely, we consider shallow networks in which biases of the neurons are frozen at random initialization. We show that the corresponding optimization landscape is benign, which in turn leads to generalization guarantees that match the near-optimal sample complexity of dedicated semi-parametric methods.

The importance of Artificial Intelligence (AI), Data Analytics and Big Data in helping business drive transformation and customer management has attracted the attention of Pension Fund Administrators(PFAs) and players in the pension industry. According them, these have a key role to play in shaping how industries evolve, and has become a massive force driving the transformation of all businesses in today's world. With this in mind the Pension Fund Operators Association of Nigeria (PenOp) recently put together a seminar for the industry to educate and show the benefits of adopting AI and data analytics. The seminar was tagged: "What has Data Analytics, Artificial Intelligence (AI) and Big Data got to do with Pensions?'' The online session, which was open to pension professionals sought to answer questions such as: What does AI have to do with the pension industry?

Dr. Stephen Thaler developed DABUS (Device for Autonomous Bootstrapping of Unified Science), an artificial intelligence (AI) system that can autonomously create patentable inventions. Thaler has filed patent applications in various jurisdictions for two inventions created by DABUS – a food container with side walls having a fractal profile, and a beacon for attracting enhanced attention for example in a search and rescue scenario[1]. In each application, Thaler listed DABUS as the sole inventor, forcing patent offices in various jurisdictions to address the issue of whether an AI system can be an inventor on a patent application. Thus far, the DABUS patent applications have found very limited success in patent offices and courts around the world. In the latest decision, the United States Court of Appeals for the Federal Circuit (CAFC) held that the US Patent Act requires an inventor to be a natural person, and consequently, an AI system cannot be an inventor on a United States patent application.[2] The DABUS applications were initially rejected by the United States Patent and Trademark Office (USPTO).

The status quo in retail banking is tottering. This has forced banks and credit unions to modify their business models, re-prioritize investments, change products and services offered and ramp up innovation efforts. There has also been a rethinking of distribution options, with digital channels significantly increasing in importance. These shifts are reflected in the sixth iteration of a study of the future of retail banking conducted by The Economist Intelligence Unit, on behalf of Temenos. Until recently, the changes in consumer behavior were believed to be the primary impetus for changes in retail banking strategies.

The wide scale adoption of Artificial Intelligence (AI) software is one of the great transformational technologies of the 21st Century. It is also big business. The global market for AI was estimated at $387.45 billion in 2022 and is expected to reach $1.394 trillion by 2029, according to Fortune Business Insight. One company that is helping to accelerate that transformation, is AI pioneer C3 AI (NYSE: AI). Founded in 2009 long before the wide adoption of either the Cloud or AI by legendary Silicon Valley entrepreneur and billionaire Tom Siebel, C3 provides an open model-AI architecture that simplifies data science and application development to offer an end-to-end platform for developing, deploying, and operating large-scale AI applications; a portfolio of industry-specific SaaS AI applications; a suite of industry-specific CRM applications; and a no-code AI solution to apply data science to everyday business problems.

Environmental problems become more urgent and affect the lives of people, marine life, and various animal species. Only in 2022, forest fires in Spain, France, and many other countries worldwide led to the destruction of animals' natural habitats, a decrease in the number of air producers, and many harmful outcomes for local residents. Although it is hard to say if humanity can still stop global warming and other environmental issues, there are some ways to restrain their development, and the utilization of renewable energy sources is among them. In this article, we list the best and most innovative renewable energy companies to keep on your radar this year. Moreover, if you are seeking more information on how modern technology can help us prevent global environmental catastrophes, read these AITJ articles: 5 Ways AI Can Improve Environmental Sustainability and How AI Helps Clean Oceans from Plastics.