The use of synthetic data is recognized as a crucial step in the development of neural network-based Artificial Intelligence (AI) systems. While the methods for generating synthetic data for AI applications in other domains have a role in certain biomedical AI systems, primarily related to image processing, there is a critical gap in the generation of time series data for AI tasks where it is necessary to know how the system works. This is most pronounced in the ability to generate synthetic multi-dimensional molecular time series data (SMMTSD); this is the type of data that underpins research into biomarkers and mediator signatures for forecasting various diseases and is an essential component of the drug development pipeline. We argue the insufficiency of statistical and data-centric machine learning (ML) means of generating this type of synthetic data is due to a combination of factors: perpetual data sparsity due to the Curse of Dimensionality, the inapplicability of the Central Limit Theorem, and the limits imposed by the Causal Hierarchy Theorem. Alternatively, we present a rationale for using complex multi-scale mechanism-based simulation models, constructed and operated on to account for epistemic incompleteness and the need to provide maximal expansiveness in concordance with the Principle of Maximal Entropy. These procedures provide for the generation of SMMTD that minimizes the known shortcomings associated with neural network AI systems, namely overfitting and lack of generalizability. The generation of synthetic data that accounts for the identified factors of multi-dimensional time series data is an essential capability for the development of mediator-biomarker based AI forecasting systems, and therapeutic control development and optimization through systems like Drug Development Digital Twins.

The expansion of explainable artificial intelligence as a field of research has generated numerous methods of visualizing and understanding the black box of a machine learning model. Attribution maps are generally used to highlight the parts of the input image that influence the model to make a specific decision. On the other hand, the robustness of machine learning models to natural noise and adversarial attacks is also being actively explored. This paper focuses on evaluating methods of attribution mapping to find whether robust neural networks are more explainable. We explore this problem within the application of classification for medical imaging. Explainability research is at an impasse. There are many methods of attribution mapping, but no current consensus on how to evaluate them and determine the ones that are the best. Our experiments on multiple datasets (natural and medical imaging) and various attribution methods reveal that two popular evaluation metrics, Deletion and Insertion, have inherent limitations and yield contradictory results. We propose a new explainability faithfulness metric (called EvalAttAI) that addresses the limitations of prior metrics. Using our novel evaluation, we found that Bayesian deep neural networks using the Variational Density Propagation technique were consistently more explainable when used with the best performing attribution method, the Vanilla Gradient. However, in general, various types of robust neural networks may not be more explainable, despite these models producing more visually plausible attribution maps.

We study the single-channel source separation problem involving orthogonal frequency-division multiplexing (OFDM) signals, which are ubiquitous in many modern-day digital communication systems. Related efforts have been pursued in monaural source separation, where state-of-the-art neural architectures have been adopted to train an end-to-end separator for audio signals (as 1-dimensional time series). In this work, through a prototype problem based on the OFDM source model, we assess -- and question -- the efficacy of using audio-oriented neural architectures in separating signals based on features pertinent to communication waveforms. Perhaps surprisingly, we demonstrate that in some configurations, where perfect separation is theoretically attainable, these audio-oriented neural architectures perform poorly in separating co-channel OFDM waveforms. Yet, we propose critical domain-informed modifications to the network parameterization, based on insights from OFDM structures, that can confer about 30 dB improvement in performance.

The U.S. military said a Russian fighter plane clipped the propeller of one its spy drones and made it crash into the Black Sea on Tuesday in the first such direct encounter between the two world powers since Russia invaded Ukraine over a year ago. The Russian Defense Ministry offered a different account, and Moscow's ambassador to Washington said his country "views this incident as a provocation" involving a U.S. MQ-9 drone and Russian Su-27 fighter jet. The United States, which has provided tens of billions of dollars in military aid to Ukraine, has not become directly engaged in the war but it does conduct regular surveillance flights in the region. This could be due to a conflict with your ad-blocking or security software. Please add japantimes.co.jp and piano.io to your list of allowed sites.

ChatGPT made a splash with its user-friendly interface and believable AI-generated responses. With a single prompt, ChatGPT provided detailed answers that other AI assistants had not achieved. Powered by a massive dataset that ChatGPT had been trained on, the breadth and variety of topics it could address quickly amazed the tech industry and the public. However the technology sophistication raises inevitable question: what are the drawbacks of ChatGPT and similar technologies? With capabilities to generate a multitude of realistic responses, ChatGPT could be used to create a host of responses capable of tricking an unassuming reader into thinking a real human is behind the content.

CAMBRIDGE, MA -- March 14, 2023 -- Researchers from MIT and other institutions report that a "hash function" -- a core database search operation -- can be significantly accelerated through the use of machine learning. The hope is that the new technique could accelerate computational systems that scientists use to store and analyze DNA, amino acid sequences, or other biological information. Hashing is used in applications from database indexing to data compression to cryptography. A hash function generates codes that directly determine the location where data would be stored. But because traditional hash functions generate codes randomly, sometimes two pieces of data can be hashed with the same value.

A Russian fighter jet has hit a US military drone over international waters, crashing the drone. The MQ-9 Reaper drone and two SU-27 craft were all flying above the Black Sea, and according to the US military's European Command, the Russian planes dumped fuel on the drone and flew in front of it dangerously, and eventually one of them hit the drone's propeller, forcing the US to bring down the drone. "This unsafe and unprofessional act by the Russians nearly caused both aircraft to crash," said US Air Force commander James B. Hecker in a press release. He also stated that the drone was "conducting routine operations" and that this incident will not stop US aircraft from operating in international airspace. Drones like this one have been operating over the Black Sea since well before the beginning of the Russia-Ukraine war to monitor the situation in Ukraine.

A team of MIT engineers is designing a kit of universal robotic parts that an astronaut could easily mix and match to build different robot "species" to fit various missions on the moon. When astronauts begin to build a permanent base on the moon, as NASA plans to do in the coming years, they'll need help. Robots could potentially do the heavy lifting by laying cables, deploying solar panels, erecting communications towers, and building habitats. But if each robot is designed for a specific action or task, a moon base could become overrun by a zoo of machines, each with its own unique parts and protocols. To avoid a bottleneck of bots, a team of MIT engineers is designing a kit of universal robotic parts that an astronaut could easily mix and match to rapidly configure different robot "species" to fit various missions on the moon.

Former U.S. Ambassador to Ukraine John Herbst discusses massive missile attacks launched by Russia as the battle for city of Bakhmut rages on. A Russian Su-27 jet collided with a U.S. MQ-9 Reaper drone over the Black Sea Tuesday, a U.S. defense official told Fox News. It was one of two Su-27's flying. This happened in international airspace over international waters. The propeller to the drone was damaged and the drone landed in the Black Sea, west of Crimea, the U.S. defense official says.

Gaurav Banga is at the helm of his own company for the third time with cybersecurity specialist Balbix, having previously founded endpoint security software maker Bromium and mobile instant messaging app PDAapps. Gaurav Banga never intended to start a series of cutting-edge high-tech companies. His latest is Balbix, based in San Jose, California, one of the world's most advanced cybersecurity platforms. "I'm an accidental entrepreneur," he told Startup Savant. "While I was earning my Ph.D. in computer science at Rice University, I had intended to be an academic. But when I started applying for faculty positions, I realized I would be teaching undergraduates without knowing much about their future industry careers. So, I took a sabbatical for a year to work in industry, and I had so much fun, I never went back."