--Deep clustering has increasingly been demonstrating superiority over conventional shallow clustering algorithms. Deep clustering algorithms usually combine representation learning with deep neural networks to achieve this performance, typically optimizing a clustering and non-clustering loss. In such cases, an autoencoder is typically connected with a clustering network, and the final clustering is jointly learned by both the autoencoder and clustering network. Instead, we propose to learn an autoencoded embedding and then search this further for the underlying manifold. We study a number of local and global manifold learning methods on both the raw data and autoencoded embedding, concluding that UMAP in our framework is able to find the best clusterable manifold of the embedding. This suggests that local manifold learning on an autoencoded embedding is effective for discovering higher quality clusters. We quantitatively show across a range of image and time-series datasets that our method has competitive performance against the latest deep clustering algorithms, including outperforming current state-of-the-art on several. We postulate that these results show a promising research direction for deep clustering. Clustering is a fundamental pillar of unsupervised machine learning. It is widely used in a range of tasks across disciplines and well-known algorithms such as k -means have found success in many applications.

Representations of sequential data are commonly based on the assumption that observed sequences are realizations of an unknown underlying stochastic process, where the learning problem includes determination of the model parameters. In this context the model must be able to capture the multi-modal nature of the data, without blurring between modes. This property is essential for applications like trajectory prediction or human motion modeling. Towards this end, a neural network model for continuous-time stochastic processes usable for sequence prediction is proposed. The model is based on Mixture Density Networks using B\'ezier curves with Gaussian random variables as control points (abbrev.: $\mathcal{N}$-Curves). Key advantages of the model include the ability of generating smooth multi-mode predictions in a single inference step which reduces the need for Monte Carlo simulation, as required in many multi-step prediction models, based on state-of-the-art neural networks. Essential properties of the proposed approach are illustrated by several toy examples and the task of multi-step sequence prediction. Further, the model performance is evaluated on two real world use-cases, i.e. human trajectory prediction and human motion modeling, outperforming different state-of-the-art models.

We introduce a new algorithm for multi-objective reinforcement learning (MORL) with linear preferences, with the goal of enabling few-shot adaptation to new tasks. In MORL, the aim is to learn policies over multiple competing objectives whose relative importance (preferences) is unknown to the agent. While this alleviates dependence on scalar reward design, the expected return of a policy can change significantly with varying preferences, making it challenging to learn a single model to produce optimal policies under different preference conditions. We propose a generalized version of the Bellman equation to learn a single parametric representation for optimal policies over the space of all possible preferences. After this initial learning phase, our agent can quickly adapt to any given preference, or automatically infer an underlying preference with very few samples. Experiments across four different domains demonstrate the effectiveness of our approach.

A new challenge for knowledge graph reasoning started in 2018. Deep learning has promoted the application of artificial intelligence (AI) techniques to a wide variety of social problems. Accordingly, being able to explain the reason for an AI decision is b ecoming important to ensure the secure and safe use of AI techniques. Thus, we, the Special Interest Group on Semantic Web and Ontology of the Japanese Society for AI, organized a challenge calling for techniques that reason and/or estimate which character s are criminals while providing a reasonable explanation based on an open knowledge graph of a well - known Sherlock Holmes mystery story . This paper presents a summary report of the first challenge held in 2018, including the knowledge graph construction, t he techniques proposed for reasoning and/or estimation, the evaluation metrics, and the results. The first prize went to an approach that formalized the problem as a constraint satisfaction problem and solved it using a lightweight formal method; the secon d prize went to an approach that used SPARQL and rules; the best resource prize went to a submission that constructed word embedding of characters from all sentences of Sherlock Holmes novels; and the best idea prize went to a discussion multi - agents model . We conclude this paper with the plans and issues for the next challenge in 2019.

ConArg is a suite of tools that offers a wide series of applications for dealing with argumentation problems. In this work, we present the advances we made in implementing a ranking-based semantics, based on computational choice power indexes, within ConArg. Such kind of semantics represents a method for sorting the arguments of an abstract argumentation framework, according to some preference relation. The ranking-based semantics we implement relies on Shapley, Banzhaf, Deegan-Packel and Johnston power index, transferring well know properties from computational social choice to argumentation framework ranking-based semantics.

In this paper, we use reinforcement learning to find effective decoding strategies for binary linear codes. We start by reviewing several iterative decoding algorithms that involve a decision-making process at each step, including bit-flipping (BF) decoding, residual belief propagation, and anchor decoding. We then illustrate how such algorithms can be mapped to Markov decision processes allowing for data-driven learning of optimal decision strategies, rather than basing decisions on heuristics or intuition. As a case study, we consider BF decoding for both the binary symmetric and additive white Gaussian noise channel. Our results show that learned BF decoders can offer a range of performance-complexity trade-offs for the considered Reed-Muller and BCH codes, and achieve near-optimal performance in some cases. We also demonstrate learning convergence speed-ups when biasing the learning process towards correct decoding decisions, as opposed to relying only on random explorations and past knowledge.

Cutting-edge robots are on display at the 2019 World Robot Conference in Beijing, running from August 20 to 25, are expected to attract nearly 200 guests from 22 countries. The conference features a series of exhibition areas for new robotic technologies and products - including medical, multi-legged, and smart logistics - as well as four contests with an anticipated 4,500 professional participants. Over 700 robots specialising with more than 21 industrial applications will be exhibited between now and the close of the conference. Among those exhibiting will be HRG Robotics, whose, president Wang Meng, said: 'We will be showcasing a string of successful companies which have got off the ground through the help of HRG, alongside our representative products at WRC 2019, as we aim to form new partnerships with companies around the world.' Also on display will be SmartBird, created by German firm Festo, whose design was inspired by the herring gull and whose flight mimics that of the bird. The ultralight flying drone was created with the best aerodynamics and maximum agility in mind and it is able to take off, fly and land under its own power.

SAN FRANCISCO – Soon, you could get fewer familiar ads following you around the internet -- or at least on Facebook. Facebook is launching a long-promised tool that lets you limit what the social network can gather about you on outside websites and apps. The company said Tuesday that it is adding a section where you can see the activity that Facebook tracks outside its service via its "like" buttons and other means. You can choose to turn off the tracking; otherwise, tracking will continue the same way it has been. Formerly known as "clear history," the tool will now go by the slightly clunkier moniker "off-Facebook activity."

When humans learned to extract metals from their ores and mix them into alloys such as bronze, brass and steel, technology took great leaps forward. Now researchers are turning to artificial intelligence to find the next generation of alloys. Scientists are already finding new alloys with increased strength and other improved features. A research team based in China have now published such discoveries in the journal Acta Materialia. Explaining the origins of their work, researcher Yanjing Su of the Beijing Advanced Innovation Center for Materials Genome Engineering cites as his inspiration the success of machine learning in mastering the strategy game Go.

Last week, Eko Devices announced a new service that matches ECG and heart sound recordings with clinical data to help pinpoint novel drug-data combinations. The Silicon Valley startup is pitching the platform, called Eko Home, as a resource for clinical trials targeting new therapies. The new platform is already seeing some action. According to the company, an ongoing Mayo Clinic study exploring how carvedilol-based cardiovascular therapies could reduce heart failure or other heart function declines among breast cancer patients undergoing chemotherapy is using the Eko Home platform to drive insights. Eko -- which is best known for its Eko Duo device, a smart remote monitor that's part stethoscope, part ECG -- also said in its announcement that it "expects to offer the drug-data combinations with other life science partners by the end of the year with additional plans to offer its SDK to hospitals and healthcare providers that wish to build the platform directly into their applications."