We introduce LiPopt, a polynomial optimization framework for computing increasingly tighter upper bounds on the Lipschitz constant of neural networks. The underlying optimization problems boil down to either linear (LP) or semidefinite (SDP) programming. We show how to use the sparse connectivity of a network, to significantly reduce the complexity of computation. This is specially useful for convolutional as well as pruned neural networks. We conduct experiments on networks with random weights as well as networks trained on MNIST, showing that in the particular case of the $\ell_\infty$-Lipschitz constant, our approach yields superior estimates, compared to baselines available in the literature.

Most current studies on survey analysis and risk tolerance modelling lack professional knowledge and domain-specific models. Given the effectiveness of generative adversarial learning in cross-domain information, we design an Asymmetric cross-Domain Generative Adversarial Network (ADGAN) for domain scale inequality. ADGAN utilizes the information-sufficient domain to provide extra information to improve the representation learning on the information-insufficient domain via domain alignment. We provide data analysis and user model on two data sources: Consumer Consumption Information and Survey Information. We further test ADGAN on a real-world dataset with view embedding structures and show ADGAN can better deal with the class imbalance and unqualified data space than state-of-the-art, demonstrating the effectiveness of leveraging asymmetrical domain information.

That was really interesting, thank you Patrick for joining us. Patrick Brennan: It was a pleasure, thank you. Norman Swan: Professor Patrick Brennan, who is Professor of Diagnostic Imaging at the University of Sydney. I'm Norman Swan, this has been the Health Report on RN. And don't forget the Coronacast, our daily podcast on all things to do with the coronavirus that Tegan Taylor and I present. You can download it by going to Apple Podcasts, the ABC Listen app, or wherever you get your podcasts. I'll see you next week.

When we think of human trafficking, we often think about the despondent faces of women and children who live in slums all over the world. What if human trafficking is much closer to home than we think? In 2019, Markie Dell, stood on the TEDx stage to recount her experience of being a domestic human trafficking victim. She was an awkward teenager who was groomed by a girl that she befriended at a birthday party. She was subsequently kidnapped, drugged, sexually violated, intimidated at gunpoint into dancing in strip clubs for an entire year.

With the proliferation of AI principles worldwide1, industry is faced with a new challenge: how to implement these AI principles? Since 2017, the international committee responsible for the standardization of AI (SC 42) has been tackling this challenge: it is developing standards covering both technical and organisational specifications to enable responsible and trustworthy AI. Forty-four countries are currently involved in the work of SC 42, and Australia plays an active role in the development of the AI international standards, as it has formed standards committee IT-043 to be Australia's voice at SC 42. When it comes to AI, it is essential to provide for interoperability and global governance, and this is why AI international standards have the buy in from key governments (such as China, the US and the EU). Australia has also identified AI standards as an important national priority.

The spread of online reviews and opinions and its growing influence on people's behavior and decisions, boosted the interest to extract meaningful information from this data deluge. Hence, crowdsourced ratings of products and services gained a critical role in business and governments. Current state-of-the-art solutions rank the items with an average of the ratings expressed for an item, with a consequent lack of personalization for the users, and the exposure to attacks and spamming/spurious users. Using these ratings to group users with similar preferences might be useful to present users with items that reflect their preferences and overcome those vulnerabilities. In this paper, we propose a new reputation-based ranking system, utilizing multipartite rating subnetworks, which clusters users by their similarities using three measures, two of them based on Kolmogorov complexity. We also study its resistance to bribery and how to design optimal bribing strategies. Our system is novel in that it reflects the diversity of preferences by (possibly) assigning distinct rankings to the same item, for different groups of users. We prove the convergence and efficiency of the system. By testing it on synthetic and real data, we see that it copes better with spamming/spurious users, being more robust to attacks than state-of-the-art approaches. Also, by clustering users, the effect of bribery in the proposed multipartite ranking system is dimmed, comparing to the bipartite case.

This paper proposes a generic approach for crop anomaly detection at the parcel-level based on unsupervised point anomaly detection techniques. The input data is derived from synthetic aperture radar (SAR) and optical images acquired using Sentinel-1 and Sentinel-2 satellites. The proposed strategy consists of four sequential steps: acquisition and preprocessing of optical and SAR images, extraction of optical and SAR indicators, computation of zonal statistics at the parcel-level and point anomaly detection. This paper analyzes different factors that can affect the results of anomaly detection such as the considered features and the anomaly detection algorithm used. The proposed procedure is validated on two crop types in Beauce (France), namely, rapeseed and wheat crops. Two different parcel delineation databases are considered to validate the robustness of the strategy to changes in parcel boundaries.

Interactive recommendation aims to learn from dynamic interactions between items and users to achieve responsiveness and accuracy. Reinforcement learning is inherently advantageous for coping with dynamic environments and thus has attracted increasing attention in interactive recommendation research. Inspired by knowledge-aware recommendation, we proposed Knowledge-Guided deep Reinforcement learning (KGRL) to harness the advantages of both reinforcement learning and knowledge graphs for interactive recommendation. This model is implemented upon the actor-critic network framework. It maintains a local knowledge network to guide decision-making and employs the attention mechanism to capture long-term semantics between items. We have conducted comprehensive experiments in a simulated online environment with six public real-world datasets and demonstrated the superiority of our model over several state-of-the-art methods.

As you might expect, this year, many companies use artificial intelligence (AI) and machine learning at the core of their business to deliver innovative products and service offerings. Anyone interested in AI should know about these 14 pioneering businesses.# This London-based company was founded in 2013 and operates under two business units: BenevolentTech's focus is to develop the artificial intelligence platform that will drive innovation by transforming the way scientists access and use the information available to them. BenevolentBio is the division that applies the tech to generate new ideas that will impact human health such as better medicines and research, insights and innovation for rare diseases. With a mission to make law free and understandable, Casetext leverages artificial intelligence technology to help legal researchers find the most relevant cases quickly.

Unsupervised pre-training of large neural models has recently revolutionized Natural Language Processing. By warm-starting from the publicly released checkpoints, NLP practitioners have pushed the state-of-the-art on multiple benchmarks while saving significant amounts of compute time. So far the focus has been mainly on the Natural Language Understanding tasks. In this paper, we demonstrate the efficacy of pre-trained checkpoints for Sequence Generation. We developed a Transformer-based sequence-to-sequence model that is compatible with publicly available pre-trained BERT, GPT-2 and RoBERTa checkpoints and conducted an extensive empirical study on the utility of initializing our model, both encoder and decoder, with these checkpoints. Our models result in new state-of-the-art results on Machine Translation, Text Summarization, Sentence Splitting, and Sentence Fusion.