--Machine Learning has proven useful in the recent years as a way to achieve failure prediction for industrial systems. However, the high computational resources necessary to run learning algorithms are an obstacle to its widespread application. The sub-field of Distributed Learning offers a solution to this problem by enabling the use of remote resources but at the expense of introducing communication costs in the application that are not always acceptable. In this paper, we propose a distributed learning approach able to optimize the use of computational and communication resources to achieve excellent learning model performances through a centralized architecture. T o achieve this, we present a new centralized distributed learning algorithm that relies on the learning paradigms of Active Learning and Federated Learning to offer a communication-efficient method that offers guarantees of model precision on both the clients and the central server . We evaluate this method on a public benchmark and show that its performances in terms of precision are very close to state-of-the-art performance level of non-distributed learning despite additional constraints. A. General problem In the recent years, the efficiency of Machine Learning for automated processing of large volumes of data has been widely demonstrated. This has been of particular interest for industrial applications that commonly generate large datasets.

As MBW reports, the latest staffing changes have made waves due to the statement that came with the news citing a renewed investment in artificial intelligence. "We are modernizing our company to take advantage of the significant investments we have made in new technology and aligning our operating structure to match the technology-powered businesses we are now in," said iHeartMedia. It's believed that the 57 are mostly radio jocks carry decades of experience working across genres of music including Rock, Urban, Country, Top 40, Hits and more. "During a transition like this it's reasonable to expect that there will be some shifts in jobs – some by location and some by function – but the number is relatively small given our overall employee base of 12,500." "That said, we recognize that the loss of any job is significant; we take that responsibility seriously and have been thoughtful in the process."

Queensland is now home to a second Great Barrier Reef, allowing children and adults alike the ability to interact with the world's largest coral reef system without leaving the city. The Living Reef is the brainchild of game developers and researchers at the Queensland University of Technology's (QUT) The Cube in Brisbane. Large 10-metre-tall screens are educating visitors about the creatures of the reef as well as the environmental issues it faces now and into the future. The team is one of the first in the world to use a system where coral was grown with a method called the space colonisation algorithm to help mimic nature. "We created a system where we could grow coral mathematically using simulation software," Cube studio manager Simon Harrison said.

The chief executive of Google has called for international cooperation on regulating artificial intelligence technology to ensure it is'harnessed for good'. Sundar Pichai said that while regulation by individual governments and existing rules such as GDPR can provide a'strong foundation' for the regulation of AI, a more coordinated international effort is'critical' to making global standards work. The CEO said that history is full of examples of how'technology's virtues aren't guaranteed' and that with technological innovations come side effects. These range from internal combustion engines, which allowed people to travel beyond their own areas but also caused more accidents, to the internet, which helped people connect but also made it easier for misinformation to spread. These lessons teach us'we need to be clear-eyed about what could go wrong' in the development of AI-based technologies, he said.

Australian business leaders are confident that the looming rise of artificial intelligence-powered automation will increase employment, rather than destroy jobs, but are not moving fast enough to retrain staff for changed roles a study from Accenture has found. In a new report entitled "Future Workforce: Reworking The Revolution," Accenture refers to findings from a global study it timed to coincide with the recent World Economic Forum in Davos, which found that there is a notable disconnect between the importance organisations place on AI and automation and how much they are doing to equip staff for the change. The Australian responses to the study showed that 71 per cent of Australian senior executives think that their company will create net job gains in the next three years through AI, and 60 per cent of workers believe it will have a positive impact, rather than taking their job. Accenture's Andrew Woolf says the pace of technology change is accelerating and reskilling staff is part of the solution to the challenge. However, while 53 per cent of business leaders said human-machine collaboration was important to their strategic priorities, only 3 per cent said their organisation planned to significantly increase investment in reskilling workers in the next three years.

How can we enable machines to make sense of the world, and become better at learning? To approach this goal, I believe viewing intelligence in terms of many integral aspects, and also a universal two-term tradeoff between task performance and complexity, provides two feasible perspectives. In this thesis, I address several key questions in some aspects of intelligence, and study the phase transitions in the two-term tradeoff, using strategies and tools from physics and information. Firstly, how can we make the learning models more flexible and efficient, so that agents can learn quickly with fewer examples? Inspired by how physicists model the world, we introduce a paradigm and an AI Physicist agent for simultaneously learning many small specialized models (theories) and the domain they are accurate, which can then be simplified, unified and stored, facilitating few-shot learning in a continual way. Secondly, for representation learning, when can we learn a good representation, and how does learning depend on the structure of the dataset? We approach this question by studying phase transitions when tuning the tradeoff hyperparameter. In the information bottleneck, we theoretically show that these phase transitions are predictable and reveal structure in the relationships between the data, the model, the learned representation and the loss landscape. Thirdly, how can agents discover causality from observations? We address part of this question by introducing an algorithm that combines prediction and minimizing information from the input, for exploratory causal discovery from observational time series. Fourthly, to make models more robust to label noise, we introduce Rank Pruning, a robust algorithm for classification with noisy labels. I believe that building on the work of my thesis we will be one step closer to enable more intelligent machines that can make sense of the world.

In this paper we develop a new model for deep image clustering, using convolutional neural networks and tensor kernels. The proposed Deep Tensor Kernel Clustering (DTKC) consists of a convolutional neural network (CNN), which is trained to reflect a common cluster structure at the output of its intermediate layers. Encouraging a consistent cluster structure throughout the network has the potential to guide it towards meaningful clusters, even though these clusters might appear to be nonlinear in the input space. The cluster structure is enforced through the idea of unsupervised companion objectives, where separate loss functions are attached to layers in the network. These unsupervised companion objectives are constructed based on a proposed generalization of the Cauchy-Schwarz (CS) divergence, from vectors to tensors of arbitrary rank. Generalizing the CS divergence to tensor-valued data is a crucial step, due to the tensorial nature of the intermediate representations in the CNN. Several experiments are conducted to thoroughly assess the performance of the proposed DTKC model. The results indicate that the model outperforms, or performs comparable to, a wide range of baseline algorithms. We also empirically demonstrate that our model does not suffer from objective function mismatch, which can be a problematic artifact in autoencoder-based clustering models.

The Information Bottleneck (IB) principle offers a unified approach to many learning and prediction problems. Although optimal in an information-theoretic sense, practical applications of IB are hampered by a lack of accurate high-dimensional estimators of mutual information, its main constituent. We propose to combine IB with invertible neural networks (INNs), which for the first time allows exact calculation of the required mutual information. Applied to classification, our proposed method results in a generative classifier we call IB-INN. It accurately models the class conditional likelihoods, generalizes well to unseen data and reliably recognizes out-of-distribution examples. In contrast to existing generative classifiers, these advantages incur only minor reductions in classification accuracy in comparison to corresponding discriminative methods such as feed-forward networks. Furthermore, we provide insight into why IB-INNs are superior to other generative architectures and training procedures and show experimentally that our method outperforms alternative models of comparable complexity.

Code-mixing is the practice of alternating between two or more languages. Mostly observed in multilingual societies, its occurrence is increasing and therefore its importance. A major part of sentiment analysis research has been monolingual, and most of them perform poorly on code-mixed text. In this work, we introduce methods that use different kinds of multilingual and cross-lingual embeddings to efficiently transfer knowledge from monolingual text to code-mixed text for sentiment analysis of code-mixed text. Our methods can handle code-mixed text through a zero-shot learning. Our methods beat state-of-the-art on English-Spanish code-mixed sentiment analysis by absolute 3\% F1-score. We are able to achieve 0.58 F1-score (without parallel corpus) and 0.62 F1-score (with parallel corpus) on the same benchmark in a zero-shot way as compared to 0.68 F1-score in supervised settings. Our code is publicly available.

The lack of diversity of the Artificial Intelligence (AI) field is nowadays a concern, and several initiatives such as funding schemes and mentoring programs have been designed to fight against it. However, there is no indication on how these initiatives actually impact AI diversity in the short and long term. This work studies the concept of diversity in this particular context and proposes a small set of diversity indicators (i.e. indexes) of AI scientific events. These indicators are designed to quantify the lack of diversity of the AI field and monitor its evolution. We consider diversity in terms of gender, geographical location and business (understood as the presence of academia versus industry). We compute these indicators for the different communities of a conference: authors, keynote speakers and organizing committee. From these components we compute a summarized diversity indicator for each AI event. We evaluate the proposed indexes for a set of recent major AI conferences and we discuss their values and limitations.