Lifeboat Foundation

A team of researchers have come up with a machine learning-assisted way to detect the position of shapes including the poses of humans to an astonishing degree — using only WiFi signals.

In a yet-to-be-peer-reviewed paper, first spotted by Vice, researchers at Carnegie Mellon University came up with a deep learning method of mapping the position of multiple human subjects by analyzing the phase and amplitude of WiFi signals, and processing them using computer vision algorithms.

“The results of the study reveal that our model can estimate the dense pose of multiple subjects, with comparable performance to image-based approaches, by utilizing WiFi signals as the only input,” the team concluded in their paper.

“Liquid” neural nets, based on a worm’s nervous system, can transform their underlying algorithms on the fly, giving them unprecedented speed and adaptability.

Artificial intelligence (AI) tools have achieved promising results on numerous tasks and could soon assist professionals in various settings. In recent years, computer scientists have been exploring the potential of these tools for detecting signs of different physical and psychiatric conditions.

Depression is one of the most widespread psychiatric disorders, affecting approximately 9.5% of American adults every year. Tools that can automatically detect signs of depression might help to reduce suicide rates, as they would allow doctors to promptly identify people in need of psychological support.

Researchers at Jinhua Advanced Research Institute and Harbin University of Science and Technology have recently developed a deep learning algorithm that could detect depression from a person’s speech. This model, introduced in a paper published in Mobile Networks and Applications, was trained to recognize emotions in human speech by analyzing different relevant features.

Quantum sensing represents one of the most promising applications of quantum technologies, with the aim of using quantum resources to improve measurement sensitivity. In particular, sensing of optical phases is one of the most investigated problems, considered key to developing mass-produced technological devices.

Optimal usage of quantum sensors requires regular characterization and calibration. In general, such calibration is an extremely complex and resource-intensive task—especially when considering systems for estimating multiple parameters, due to the sheer volume of required measurements as well as the computational time needed to analyze those measurements. Machine-learning algorithms present a powerful tool to address that complexity. The discovery of suitable protocols for algorithm usage is vital for the development of sensors for precise quantum-enhanced measurements.

A particular type of machine-learning algorithm known as “reinforcement learning” (RL) relies on an intelligent agent guided by rewards: Depending on the rewards it receives, it learns to perform the right actions to achieve the desired optimization. The first experimental realizations using RL algorithms for the optimization of quantum problems have been reported only very recently. Most of them still rely on prior knowledge of the model describing the system. What is desirable is instead a completely model-free approach, which is possible when the agent’s reward does not depend on the explicit system model.

Quantum simulations of the hydroxide anion and hydroxyl radical are reported, employing variational quantum algorithms for near-term quantum devices. The energy of each species is calculated along the dissociation curve, to obtain information about the stability of the molecular species being investigated. It is shown that simulations restricted to valence spaces incorrectly predict the hydroxyl radical to be more stable than the hydroxide anion. Inclusion of dynamical electron correlation from nonvalence orbitals is demonstrated, through the integration of the variational quantum eigensolver and quantum subspace expansion methods in the workflow of N-electron valence perturbation theory, and shown to correctly predict the hydroxide anion to be more stable than the hydroxyl radical, provided that basis sets with diffuse orbitals are also employed.

Diffusion models have recently produced outstanding results on various generating tasks, including the creation of images, 3D point clouds, and molecular conformers. Ito stochastic differential equations (SDE) are a unified framework that can incorporate these models. The models acquire knowledge of time-dependent score fields through score-matching, which later directs the reverse SDE during generative sampling. Variance-exploding (VE) and variance-preserving (VP) SDE are common diffusion models. EDM offers the finest performance to date by expanding on these compositions. The existing training method for diffusion models can still be enhanced, despite achieving outstanding empirical results.

The Stable Target Field (STF) objective is a generalized variation of the denoising score-matching objective. Particularly, the high volatility of the denoising score matching (DSM) objective’s training targets can result in subpar performance. They divide the score field into three regimes to comprehend the cause of this volatility better. According to their investigation, the phenomenon mostly occurs in the intermediate regime, defined by various modes or data points having a similar impact on the scores. In other words, under this regime, it is still being determined where the noisy samples produced throughout the forward process originated. Figure 1(a) illustrates the differences between the DSM and their proposed STF objectives.

Figure 1: Examples of the DSM objective’s and our suggested STF objective’s contrasts.

Scientists and roboticists have long looked at nature for inspiration to develop new features for machines. In this case, researchers from Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland were inspired by bats and other animals that rely on echolocation to design a method that would give small robots that ability to navigate themselves — one that doesn’t need expensive hardware or components too large or too heavy for tiny machines. In fact, according to PopSci, the team only used the integrated audio hardware of an interactive puck robot and built an audio extension deck using cheap mic and speakers for a tiny flying drone that can fit in the palm of your hand.

The system works just like bat echolocation. It was designed to emit sounds across frequencies, which a robot’s microphone then picks up as they bounce off walls. An algorithm the team created then goes to work to analyze sound waves and create a map with the room’s dimensions.

In a paper published in IEEE Robotics and Automation Letters, the researchers said existing “algorithms for active echolocation are less developed and often rely on hardware requirements that are out of reach for small robots.” They also said their “method is model-based, runs in real time and requires no prior calibration or training.” Their solution could give small machines the capability to be sent on search-and-rescue missions or to previously uncharted locations that bigger robots wouldn’t be able to reach. And since the system only needs onboard audio equipment or cheap additional hardware, it has a wide range of potential applications.

Engineers at the University of Waterloo have developed artificial intelligence (AI) technology to predict if women with breast cancer would benefit from chemotherapy prior to surgery.

The new AI algorithm, part of the open-source Cancer-Net initiative led by Dr. Alexander Wong, could help unsuitable candidates avoid the serious side effects of chemotherapy and pave the way for better surgical outcomes for those who are suitable.

“Determining the right treatment for a given breast cancer patient is very difficult right now, and it is crucial to avoid unnecessary side effects from using treatments that are unlikely to have real benefit for that patient,” said Wong, a professor of systems design engineering.

Architectures based on artificial neural networks (ANNs) have proved to be very helpful in research settings, as they can quickly analyze vast amounts of data and make accurate predictions. In 2020, Google’s British AI subsidiary DeepMind used a new ANN architecture dubbed the Fermionic neural network (FermiNet) to solve the Schrodinger equation for electrons in molecules, a central problem in the field of chemistry.

The Schroedinger equation is a partial differential equation based on well-established theory of energy conservation, which can be used to derive information about the behavior of electrons and solve problems related to the properties of matter. Using FermiNet, which is a conceptually simple method, DeepMind could solve this equation in the context of chemistry, attaining very accurate results that were comparable to those obtained using highly sophisticated quantum chemistry techniques.

Researchers at Imperial College London, DeepMind, Lancaster University, and University of Oxford recently adapted the FermiNet architecture to tackle a quantum physics problem. In their paper, published in Physical Review Letters, they specifically used FermiNet to calculate the ground states of periodic Hamiltonians and study the homogenous electron gas (HEG), a simplified quantum mechanical model of electrons interacting in solids.