Understanding the structure of loss landscape of deep neural networks (DNNs) is obviously important. In this work, we prove an embedding principle that the loss landscape of a DNN "contains" all the critical points of all the narrower DNNs. More precisely, we propose a critical embedding such that any critical point, e.g., local or global minima, of a narrower DNN can be embedded to a critical point/hyperplane of the target DNN with higher degeneracy and preserving the DNN output function. The embedding structure of critical points is independent of loss function and training data, showing a stark difference from other nonconvex problems such as protein-folding. Empirically, we find that a wide DNN is often attracted by highly-degenerate critical points that are embedded from narrow DNNs. The embedding principle provides an explanation for the general easy optimization of wide DNNs and unravels a potential implicit low-complexity regularization during the training. Overall, our work provides a skeleton for the study of loss landscape of DNNs and its implication, by which a more exact and comprehensive understanding can be anticipated in the near future.

Automatically tuning software configuration for optimizing a single performance attribute (e.g., minimizing latency) is not trivial, due to the nature of the configuration systems (e.g., complex landscape and expensive measurement). To deal with the problem, existing work has been focusing on developing various effective optimizers. However, a prominent issue that all these optimizers need to take care of is how to avoid the search being trapped in local optima -- a hard nut to crack for software configuration tuning due to its rugged and sparse landscape, and neighboring configurations tending to behave very differently. Overcoming such in an expensive measurement setting is even more challenging. In this paper, we take a different perspective to tackle this issue. Instead of focusing on improving the optimizer, we work on the level of optimization model. We do this by proposing a meta multi-objectivization model (MMO) that considers an auxiliary performance objective (e.g., throughput in addition to latency). What makes this model unique is that we do not optimize the auxiliary performance objective, but rather use it to make similarly-performing while different configurations less comparable (i.e. Pareto nondominated to each other), thus preventing the search from being trapped in local optima. Experiments on eight real-world software systems/environments with diverse performance attributes reveal that our MMO model is statistically more effective than state-of-the-art single-objective counterparts in overcoming local optima (up to 42% gain), while using as low as 24% of their measurements to achieve the same (or better) performance result.

Event detection (ED) aims at detecting event trigger words in sentences and classifying them into specific event types. In real-world applications, ED typically does not have sufficient labelled data, thus can be formulated as a few-shot learning problem. To tackle the issue of low sample diversity in few-shot ED, we propose a novel knowledge-based few-shot event detection method which uses a definition-based encoder to introduce external event knowledge as the knowledge prior of event types. Furthermore, as external knowledge typically provides limited and imperfect coverage of event types, we introduce an adaptive knowledge-enhanced Bayesian meta-learning method to dynamically adjust the knowledge prior of event types. Experiments show our method consistently and substantially outperforms a number of baselines by at least 15 absolute F1 points under the same few-shot settings.

Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they fail to fully utilize the structure information of the input graph. In this paper, we aim to further improve the performance of the pre-trained language model by proposing a structured graph-to-text model with a two-step fine-tuning mechanism which first fine-tunes the model on Wikipedia before adapting to the graph-to-text generation. In addition to using the traditional token and position embeddings to encode the knowledge graph (KG), we propose a novel tree-level embedding method to capture the inter-dependency structures of the input graph. This new approach has significantly improved the performance of all text generation metrics for the English WebNLG 2017 dataset.

There are 15 Chapters to display the Global Artificial Intelligence in Platform as a Service (PaaS) Market Chapter 1, Overview to describe Definition, Specifications and Classification of Global Artificial Intelligence in Platform as a Service (PaaS) market, Applications [SME & Large Enterprises], Market Segment by Types, Machine Learning Platform, Natural Language Processing Service, Visual Analysis Service, Language Processing Service & Data Insight Service; Chapter 2, objective of the study.

GlobalData has identified ten of the biggest influencers in AI on Twitter during Q3 2019, using its Influencer Platform. GlobalData research has found the top AI influencers based on their performance and engagement online. Using research from GlobalData's Influencer platform, Verdict has named ten of the most influential people in AI on Twitter during Q3 2019. Ronald van Loon is a Big Data expert and Director at Advertisement, a data and analytics consultancy firm. He helps data-driven companies in executing data and analytics strategies to become more successful.

Technological advancements have been influencing our lives for quite some time already and still continue to do the same. Lately, the role and importance of Artificial Intelligence (AI) have risen at significant heights. It has an impact on every industry and every single aspect of our lives. Australia, as well as other countries all around the world, is facing challenges that are not easy to overcome, for example, management of natural hazards, aging population, health, infrastructure, etc, and surprisingly or not, AI has the ability to provide them with the proper help. The term Artificial Intelligence has been used to describe the technique that analyzes the threat or challenge and helps us to solve them.

"Together they created Appen, arguably one of the greatest IT success stories in Australia," said University of Sydney Vice-Chancellor and Principal Professor Stephen Garton AM. "Their company was founded long before artificial intelligence became fashionable and is a testament to the foresight of the Vonwillers." Honorary degrees are awarded to individuals who have made an outstanding contribution to the wider community or who have achieved exceptional academic or creative excellence. Husband and wife team Chris and Julia Vonwiller have been admitted to the degree of Doctor of Engineering (honoris causa). Dr Vonwiller is a respected linguist who studied at Macquarie University and graduated in 1980 with a Bachelor of Arts (Honours). She completed her PhD in linguistics at Macquarie University in 1989 before working as a researcher at the University of Sydney.

With the advent of Artificial Intelligence (AI)-empowered communications, industry, academia, and standardization organizations are progressing on the definition of mechanisms and procedures to address the increasing complexity of future 5G and beyond communications. In this context, the International Telecommunication Union (ITU) organized the first AI for 5G Challenge to bring industry and academia together to introduce and solve representative problems related to the application of Machine Learning (ML) to networks. In this paper, we present the results gathered from Problem Statement~13 (PS-013), organized by Universitat Pompeu Fabra (UPF), which primary goal was predicting the performance of next-generation Wireless Local Area Networks (WLANs) applying Channel Bonding (CB) techniques. In particular, we overview the ML models proposed by participants (including Artificial Neural Networks, Graph Neural Networks, Random Forest regression, and gradient boosting) and analyze their performance on an open dataset generated using the IEEE 802.11ax-oriented Komondor network simulator. The accuracy achieved by the proposed methods demonstrates the suitability of ML for predicting the performance of WLANs. Moreover, we discuss the importance of abstracting WLAN interactions to achieve better results, and we argue that there is certainly room for improvement in throughput prediction through ML.

Studying the implicit regularization effect of the nonlinear training dynamics of neural networks (NNs) is important for understanding why over-parameterized neural networks often generalize well on real dataset. Empirically, existing works have shown that weights of NNs condense on isolated orientations with a small initialization. The condensation dynamics implies that NNs can learn features from the training data with a network configuration effectively equivalent to a much smaller network during the training. In this work, we show that the multiple roots of activation function at origin is a key factor to understanding the condensation at the initial stage of training. Our experiments suggest that the maximal number of condensed orientations is twice of the multiplicity. Our theoretical analysis confirms experiments for two cases, one is for the activation function of multiplicity one and the other is for the one-dimensional input. This work makes a step towards understanding how small initialization implicitly leads NNs to condensation at initial stage of training, which lays a solid foundation for the future study of the nonlinear dynamics of NNs and its implicit regularization effect at a later stage of training.