Fig 1.1 Memory and non-memory components relationship Fig 1.2 Concept of artificial neural system in neuromorphic devices Fig 2.1 Memristor Symbol Fig 2.2 Current-voltage pinched hysteresis curve of memristor Fig 2.3 Memcapacitor Symbol Fig 2.4 Charge-voltage pinched hysteresis curve of memcapacitor Fig 2.5 Meminductor Symbol Fig 2.6 Current-flux pinched hysteresis curve of meminductor Fig 3.1 Device structure (a) TiOx-based memristor device (b) Si-based memcapacitor device Fig 3.2 Distribution of the TiOx memristor conductance in the HRS and LRS Fig 3.3 Training accuracy comparison of non-idealities (a) different device-todevice memductance variation (b) different cycle-to-cycle variation. Fig 3.4 The accuracy is influenced by the line resistance and the sneak paths Fig 3.5 Transistor level used in the framework (a) current sense amplifier (CSA), (b) voltage sense amplifier (VSA), (c) level shifter, and (d) successive approximation register (SAR) ADC. Fig 4.1 OTA (a) Symbol representation, and (b) MOSFETs realization Fig 4.2 Proposed meminductor emulator circuit Fig 4.3 An RLC neuromorphic circuit using meminductor for amoeba behavior Fig 4.4 Neuromorphic circuit using a meminductor for amoeba behavior Fig 4.5 Photograph of experimental setup Fig 4.6 Schematic of the hardware-implemented convolution layer Fig 4.7 Flowchart of CNN model training Fig 4.8 Structure of CNN implemented in software for classification of MNIST dataset Fig 4.9 Proposed meminductor based (a) VMM accelerator.

Federated Learning (FL) is a machine learning (ML) approach that enables multiple decentralized devices or edge servers to collaboratively train a shared model without exchanging raw data. During the training and sharing of model updates between clients and servers, data and models are susceptible to different data-poisoning attacks. In this study, our motivation is to explore the severity of data poisoning attacks in the computer network domain because they are easy to implement but difficult to detect. We considered two types of data-poisoning attacks, label flipping (LF) and feature poisoning (FP), and applied them with a novel approach. In LF, we randomly flipped the labels of benign data and trained the model on the manipulated data. For FP, we randomly manipulated the highly contributing features determined using the Random Forest algorithm. The datasets used in this experiment were CIC and UNSW related to computer networks. We generated adversarial samples using the two attacks mentioned above, which were applied to a small percentage of datasets. Subsequently, we trained and tested the accuracy of the model on adversarial datasets. We recorded the results for both benign and manipulated datasets and observed significant differences between the accuracy of the models on different datasets. From the experimental results, it is evident that the LF attack failed, whereas the FP attack showed effective results, which proved its significance in fooling a server. With a 1% LF attack on the CIC, the accuracy was approximately 0.0428 and the ASR was 0.9564; hence, the attack is easily detectable, while with a 1% FP attack, the accuracy and ASR were both approximately 0.9600, hence, FP attacks are difficult to detect. We repeated the experiment with different poisoning percentages.

The pursuit of optimizing cancer therapies is significantly advanced by the accurate prediction of drug synergy. Traditional methods, such as clinical trials, are reliable yet encumbered by extensive time and financial demands. The emergence of high-throughput screening and computational innovations has heralded a shift towards more efficient methodologies for exploring drug interactions. In this study, we present VQSynergy, a novel framework that employs the Vector Quantization (VQ) mechanism, integrated with gated residuals and a tailored attention mechanism, to enhance the precision and generalizability of drug synergy predictions. Our findings demonstrate that VQSynergy surpasses existing models in terms of robustness, particularly under Gaussian noise conditions, highlighting its superior performance and utility in the complex and often noisy domain of drug synergy research. This study underscores the potential of VQSynergy in revolutionizing the field through its advanced predictive capabilities, thereby contributing to the optimization of cancer treatment strategies.

Inspired by the concept of active learning, we propose active inference$\unicode{x2013}$a methodology for statistical inference with machine-learning-assisted data collection. Assuming a budget on the number of labels that can be collected, the methodology uses a machine learning model to identify which data points would be most beneficial to label, thus effectively utilizing the budget. It operates on a simple yet powerful intuition: prioritize the collection of labels for data points where the model exhibits uncertainty, and rely on the model's predictions where it is confident. Active inference constructs provably valid confidence intervals and hypothesis tests while leveraging any black-box machine learning model and handling any data distribution. The key point is that it achieves the same level of accuracy with far fewer samples than existing baselines relying on non-adaptively-collected data. This means that for the same number of collected samples, active inference enables smaller confidence intervals and more powerful p-values. We evaluate active inference on datasets from public opinion research, census analysis, and proteomics.

Learn how to protect yourself from cybercrimes with useful tips and tricks from tech expert Kim Komando like turning off your location services and Bluetooth.

On February 22nd, a robotic lander named Odysseus touched down on the sun-washed highlands near the south pole of the moon. It was the first time since the Apollo 17 mission, fifty-two years ago, that an American spacecraft had gracefully landed on the lunar surface. And yet NASA hadn't designed or built Odysseus; it was renting space onboard. Intuitive Machines, a relatively small aerospace firm based in Houston, was responsible for the lander, which launched atop a SpaceX rocket. The event was historic not just because it signalled a return to the moon but because it was the first time that a private company from any country had landed a spacecraft there.

How should we regulate AI? There's little doubt that artificial intelligence will be subject to more regulation in the years ahead. Major tech companies have requested it, and multiple countries and regions are now moving forward with plans to pass new rules governing the technology's development or use. Broadly speaking, these proposed policies aim to redirect AI toward serving societal goals or address potential biases that put people at risk.

Congress might consider new legislation on artificial intelligence and its effect on elections this year, according to the chair of the House of Representatives' new AI task force. "I do hope that we're going to be able to get started on actually creating and passing some legislation. I think that we're fortunate that there are some things that are very pressing on AI, but there's other things that relate to medium-term and long-term threats that don't need to be acted on immediately," Rep. Jay Obernolte, R-Calif., told Fox News Digital in an interview. "But those short-term threats, I think we can mitigate those this year and I'm hopeful that the task force – we'll be able to get that done." Asked to elaborate on short-term legislative goals, Obernolte said, "We have an election coming up – the use of AI to spread myths and disparate information about candidates, I think, is something we should all be able to agree is not only a bad thing for society, but something that could be a threat to people's trust in our democracy."

Another widely viewed AI image the BBC investigation found shows Mr Trump posing with black voters on a front porch. It had originally been posted by a satirical account that generates images of the former president, but only gained widespread attention when it was reposted with a new caption falsely claiming that he had stopped his motorcade to meet these people.

ABSTRACT Prediction of the Solar Energetic Particle (SEP) events garner increasing interest as space missions extend beyond Earth's protective magnetosphere. These events, which are, in most cases, products of magnetic reconnection-driven processes during solar flares or fast coronal-mass-ejection-driven shock waves, pose significant radiation hazards to aviation, space-based electronics, and particularly, space exploration. In this work, we utilize the recently developed dataset that combines the Solar Dynamics Observatory/Helioseismic and Magnetic Imager's (SDO/HMI) Space weather HMI Active Region Patches (SHARP) and the Solar and Heliospheric Observatory/Michelson Doppler Imager's (SoHO/MDI) Space Weather MDI Active Region Patches (SMARP). We employ a suite of machine learning strategies, including Support Vector Machines (SVM) and regression models, to evaluate the predictive potential of this new data product for a forecast of post-solar flare SEP events. Our study indicates that despite the augmented volume of data, the prediction accuracy reaches 0.7 0.1, which aligns with but does not exceed these published benchmarks. A linear SVM model with training and testing configurations that mimic an operational setting (positive-negative imbalance) reveals a slight increase (+0.04 0.05) in the accuracy of a 14-hour SEP forecast compared to previous studies. This outcome emphasizes the imperative for more sophisticated, physics-informed models to better understand the underlying processes leading to SEP events. INTRODUCTION Solar Energetic Particle (SEP) events are one of the manifestations of solar activity that may significantly impact the conditions of the space environment. For example, the large solar particle event of September 2017 emphasized a significant surge in the charged and neutral particle flux that was able to reach Mars' surface (Zeitlin et al. 2018). While the doses from this specific event were below NASA's stipulated radiation exposure limits for astronauts, the risk for future explorers is evident. This concern becomes particularly relevant in scenarios where human explorers might be far from their habitats on other celestial bodies, with the onset of an event leaving them vulnerable to enhanced radiation doses. Therefore, forecasting and predicting SEP events is paramount. SEP events vary in intensity, spanning from suprathermal (few keV) up to relativistic (few GeV) energies, and are accelerated near the Sun either by magnetic reconnection-driven processes during solar flares or by fast Coronal Mass Ejections (CME).