Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential equation units (DEUs), an improvement to modern neural networks, which enables each neuron to learn a particular nonlinear activation function from a family of solutions to an ordinary differential equation. Specifically, each neuron may change its functional form during training based on the behavior of the other parts of the network. We show that using neurons with DEU activation functions results in a more compact network capable of achieving comparable, if not superior, performance when is compared to much larger networks.

The majority of multi-agent system (MAS) implementations aim to optimise agents' policies with respect to a single objective, despite the fact that many real-world problem domains are inherently multi-objective in nature. Multi-objective multi-agent systems (MOMAS) explicitly consider the possible trade-offs between conflicting objective functions. We argue that, in MOMAS, such compromises should be analysed on the basis of the utility that these compromises have for the users of a system. As is standard in multi-objective optimisation, we model the user utility using utility functions that map value or return vectors to scalar values. This approach naturally leads to two different optimisation criteria: expected scalarised returns (ESR) and scalarised expected returns (SER). We develop a new taxonomy which classifies multi-objective multi-agent decision making settings, on the basis of the reward structures, and which and how utility functions are applied. This allows us to offer a structured view of the field, to clearly delineate the current state-of-the-art in multi-objective multi-agent decision making approaches and to identify promising directions for future research. Starting from the execution phase, in which the selected policies are applied and the utility for the users is attained, we analyse which solution concepts apply to the different settings in our taxonomy. Furthermore, we define and discuss these solution concepts under both ESR and SER optimisation criteria. We conclude with a summary of our main findings and a discussion of many promising future research directions in multi-objective multi-agent systems.

A group of high-tech scammers used an artificial intelligence program to pull off a $243,000 theft. According to a report in the Wall Street Journal, the thieves called the managing director of an unidentified British Energy company pretending to be his boss, the CEO of the firm's parent company. The scammers used the software to imitate the CEO's voice and managed to convince the director to wire the money to a Hungarian bank account, claiming it was meant to pay a supplier. A source who works for the energy firm's insurance company told the Washington Post that the director thought the request was "rather strange" but completed the transfer because he genuinely believed that he was speaking to his boss. Authorities have not located the people responsible for the theft and are worried that this tactic could be used in the future, especially as voice-replicating software improves and becomes easier to use.

Leveraging AI and IoT for environmental sustainability can help maximize our current efforts for environmental protection. According to a 2018 report by Intel, 74% of 200 business decision-makers in environmental sustainability agreed that AI would help solve environmental problems. Millions of electronic devices are discarded without proper disposal. Billions of dollars are wasted every year for proper disposal or recycling of used parts of discarded devices. To mitigate the issue of improper disposal of redundant electronic devices, companies like Apple use recycled materials or materials which have a low harmful impact on the environment.

SqwidNet, in partnership with Sigfox, has concluded the second round of its Internet of Things (IoT) SA University Challenge with ten university teams competing in the final pitch presentation day this week. The programme is designed to challenge students to develop and create innovative projects focused on building solutions that support the UN Sustainable Development Goals using SqwidNet/Sigfox technology. "We were astounded by the creative thinking displayed by the ten teams that presented their solutions to the judges this week," says Phathizwe Malinga, managing director of SqwidNet. "The solutions presented ranged from agricultural solutions for early pest detection to avoid crop losses, to generating electricity from plants by collecting electrons from roots in an anode and converting that into electricity. We also saw an IoT water monitoring solution, an early fire detection for rural communities and a two-way learning solution using artificial intelligence."

Before assessing its potential impact on the oil and gas sector, it's important to stress that AI is not just one algorithm, tool, platform or process. Rather it is an ecosystem of technologies and capabilities, each of which is able to replace or augment certain human competencies. AI can emulate human cognitive abilities, and therefore augment or replace them under the right conditions. In some cases, AI can detect patterns in sensory data that reveal signals beyond the boundaries of normal human perception, or in areas people would not typically be able to access. For example, sensors embedded in a storage tank may be able to recognize concentrations of different chemical elements stored in the tank.

He holds a Masters Degree in Media Arts & Sciences from Massachusetts Institute of Technology, (MIT) Media Lab at Cambridge, Massachusetts. He holds several US patents and international publications in the areas of AI, Computational Imaging, Signal processing, Cryptography. He also represents India on the International Standards Organization (ISO) committee for standards setting in Artificial Intelligence. He has also been an invited reviewer at international journal and conferences like ACM Siggraph, ACM Siggraph Asia, IEEE CVPR, ECCV, ICCP etc and has also been a TEDx Speaker. He has led business units in diverse areas of Mobile Apps, Mobile Network Performance and Security, Solar Energy, Internet of Things, Electric Vehicle Car Charging & Battery Storage.

A hierarchical Bayesian classifier is trained at pixel scale with spectral data from the CRISM (Compact Reconnaissance Imaging Spectrometer for Mars) imagery. Its utility in detecting rare phases is demonstrated with new geologic discoveries near the Mars-2020 rover landing site. Akaganeite is found in sediments on the Jezero crater floor and in fluvial deposits at NE Syrtis. Jarosite and silica are found on the Jezero crater floor while chlorite-smectite and Al phyllosilicates are found in the Jezero crater walls. These detections point to a multi-stage, multi-chemistry history of water in Jezero crater and the surrounding region and provide new information for guiding the Mars-2020 rover's landed exploration. In particular, the akaganeite, silica, and jarosite in the floor deposits suggest either a later episode of salty, Fe-rich waters that post-date Jezero delta or groundwater alteration of portions of the Jezero sedimentary sequence.

Adaptive filters are applied in several electronic and communication devices like smartphones, advanced headphones, DSP chips, smart antenna, and teleconference systems. Also, they have application in many areas such as system identification, channel equalization, noise reduction, echo cancellation, interference cancellation, signal prediction, and stock market. Therefore, reducing the energy consumption of the adaptive filtering algorithms has great importance, particularly in green technologies and in devices using battery. In this thesis, data-selective adaptive filters, in particular the set-membership (SM) adaptive filters, are the tools to reach the goal. There are well known SM adaptive filters in literature. This work introduces new algorithms based on the classical ones in order to improve their performances and reduce the number of required arithmetic operations at the same time. Therefore, firstly, we analyze the robustness of the classical SM adaptive filtering algorithms. Secondly, we extend the SM technique to trinion and quaternion systems. Thirdly, by combining SM filtering and partial-updating, we introduce a new improved set-membership affine projection algorithm with constrained step size to improve its stability behavior. Fourthly, we propose some new least-mean-square (LMS) based and recursive least-squares based adaptive filtering algorithms with low computational complexity for sparse systems. Finally, we derive some feature LMS algorithms to exploit the hidden sparsity in the parameters.

We recently outlined the vision of "Learning Everywhere" which captures the possibility and impact of how learning methods and traditional HPC methods can be coupled together. A primary driver of such coupling is the promise that Machine Learning (ML) will give major performance improvements for traditional HPC simulations. Motivated by this potential, the ML around HPC class of integration is of particular significance. In a related follow-up paper, we provided an initial taxonomy for integrating learning around HPC methods. In this paper, which is part of the Learning Everywhere series, we discuss "how" learning methods and HPC simulations are being integrated to enhance effective performance of computations. This paper identifies several modes --- substitution, assimilation, and control, in which learning methods integrate with HPC simulations and provide representative applications in each mode. This paper discusses some open research questions and we hope will motivate and clear the ground for MLaroundHPC benchmarks.