Distributed Machine Learning suffers from the bottleneck of synchronization to all-reduce workers' updates. Previous works mainly consider better network topology, gradient compression, or stale updates to speed up communication and relieve the bottleneck. However, all these works ignore the importance of reducing the scale of synchronized elements and inevitable serial executed operators. To address the problem, our work proposes the Divide-and-Shuffle Synchronization(DS-Sync), which divides workers into several parallel groups and shuffles group members. DS-Sync only synchronizes the workers in the same group so that the scale of a group is much smaller. The shuffle of workers maintains the algorithm's convergence speed, which is interpreted in theory. Comprehensive experiments also show the significant improvements in the latest and popular models like Bert, WideResnet, and DeepFM on challenging datasets.

Emerging cross-device artificial intelligence (AI) applications require a transition from conventional centralized learning systems towards large-scale distributed AI systems that can collaboratively perform complex learning tasks. In this regard, democratized learning (Dem-AI) (Minh et al. 2020) lays out a holistic philosophy with underlying principles for building large-scale distributed and democratized machine learning systems. The outlined principles are meant to provide a generalization of distributed learning that goes beyond existing mechanisms such as federated learning. Inspired from this philosophy, a novel distributed learning approach is proposed in this paper. The approach consists of a self-organizing hierarchical structuring mechanism based on agglomerative clustering, hierarchical generalization, and corresponding learning mechanism. Subsequently, a hierarchical generalized learning problem in a recursive form is formulated and shown to be approximately solved using the solutions of distributed personalized learning problems and hierarchical generalized averaging mechanism. To that end, a distributed learning algorithm, namely DemLearn and its variant, DemLearn-P is proposed. Extensive experiments on benchmark MNIST and Fashion-MNIST datasets show that proposed algorithms demonstrate better results in the generalization performance of learning model at agents compared to the conventional FL algorithms. Detailed analysis provides useful configurations to further tune up both the generalization and specialization performance of the learning models in Dem-AI systems.

The great amount of datasets generated by various data sources have posed the challenge to machine learning algorithm selection and hyperparameter configuration. For a specific machine learning task, it usually takes domain experts plenty of time to select an appropriate algorithm and configure its hyperparameters. If the problem of algorithm selection and hyperparameter optimization can be solved automatically, the task will be executed more efficiently with performance guarantee. Such problem is also known as the CASH problem. Early work either requires a large amount of human labor, or suffers from high time or space complexity. In our work, we present Auto-CASH, a pre-trained model based on meta-learning, to solve the CASH problem more efficiently. Auto-CASH is the first approach that utilizes Deep Q-Network to automatically select the meta-features for each dataset, thus reducing the time cost tremendously without introducing too much human labor. To demonstrate the effectiveness of our model, we conduct extensive experiments on 120 real-world classification datasets. Compared with classical and the state-of-art CASH approaches, experimental results show that Auto-CASH achieves better performance within shorter time.

Anomaly detection has been an active research area for several decades, with early exploration dating back as far as to 1960s [52]. Due to the increasing demand and applications in broad domains, such as risk management, compliance, security, financial surveillance, health and medical risk, and AI safety, anomaly detection plays increasingly important roles, highlighted in various communities including data mining, machine learning, computer vision and statistics. In recent years, deep learning has shown tremendous capabilities in learning expressive representations of complex data such as high-dimensional data, temporal data, spatial data and graph data, pushing the boundaries of different learning tasks.

VAPAR an Australian startup in the Internet of Things arena which utilises artificial intelligence (AI) and machine learning (ML) to automate condition assessments for stormwater and sewerage pipelines, has raised $AU700,000 in seed funding. The funding round closed with a diverse range of angel investors in addition to Startmate and Australia's premier VC, Blackbird Ventures, who are also investors in Canva, SafetyCulture, and Culture Amp. The company, which began two years ago started says it aims to bring emerging technology into the traditional asset management space and revolutionise the way infrastructure is tracked, repaired and maintained. Co-founders Amanda Siqueira, CEO, and Michelle Aguilar, CTO, said they started the business after witnessing first-hand the tedious and time-consuming tasks of manual video inspection. Their software is used by water utilities and local councils to reduce the time needed for inspection reviews.

When you hear Artificial Intelligence (AI) the first thing that comes to mind are robots; in particular, the Steven Spielberg movie titled A.I. where a robot child is built that can love and behave just like a real human. This idea appears to be closer to a dream than reality. Truth is, AI is more ubiquitous than we might think. It ranges from self-driving cars, movie recommendations on Netflix, e-mail spam detection to voice-controlled assistants such as Apple's SIRI. The fact is that AI is already present across many businesses and various industries, as is shown in the figure below.

Intern at our partner companies for 12-16 weeks and gain first hand industry experience. Most of the companies hire our interns for Entry level and Experienced roles before closure of internships. Take part of in-house research on AI, IoT, VLSI and ML for 12-16 weeks and solve industry challenges.... Interested students opt for full time research in-house or co-innovation at a collaborating university. Most of our students started at DesignNation, are now pursuing PhD and Post-doctoral studies at USA, Canada and Australia. More than 70% jobs, now are upgraded to new technologies. Get ready for change and avail better pay by upgrading... yourself to new technologies.

The fuzzy integral is a powerful parametric nonlin-ear function with utility in a wide range of applications, from information fusion to classification, regression, decision making,interpolation, metrics, morphology, and beyond. While the fuzzy integral is in general a nonlinear operator, herein we show that it can be represented by a set of contextual linear order statistics(LOS). These operators can be obtained via sampling the fuzzy measure and clustering is used to produce a partitioning of the underlying space of linear convex sums. Benefits of our approach include scalability, improved integral/measure acquisition, generalizability, and explainable/interpretable models. Our methods are both demonstrated on controlled synthetic experiments, and also analyzed and validated with real-world benchmark data sets.

This paper describes our submission to subtask a and b of SemEval-2020 Task 4. For subtask a, we use a ALBERT based model with improved input form to pick out the common sense statement from two statement candidates. For subtask b, we use a multiple choice model enhanced by hint sentence mechanism to select the reason from given options about why a statement is against common sense. Besides, we propose a novel transfer learning strategy between subtasks which help improve the performance. The accuracy scores of our system are 95.6 / 94.9 on official test set and rank 7$^{th}$ / 2$^{nd}$ on Post-Evaluation leaderboard.

In this paper, we elaborate on the use of the Sugeno integral in the context of machine learning. More specifically, we propose a method for binary classification, in which the Sugeno integral is used as an aggregation function that combines several local evaluations of an instance, pertaining to different features or measurements, into a single global evaluation. Due to the specific nature of the Sugeno integral, this approach is especially suitable for learning from ordinal data, that is, when measurements are taken from ordinal scales. This is a topic that has not received much attention in machine learning so far. The core of the learning problem itself consists of identifying the capacity underlying the Sugeno integral. To tackle this problem, we develop an algorithm based on linear programming. The algorithm also includes a suitable technique for transforming the original feature values into local evaluations (local utility scores), as well as a method for tuning a threshold on the global evaluation. To control the flexibility of the classifier and mitigate the problem of overfitting the training data, we generalize our approach toward $k$-maxitive capacities, where $k$ plays the role of a hyper-parameter of the learner. We present experimental studies, in which we compare our method with competing approaches on several benchmark data sets.