The COVID-19 pandemic has caused drastic alternations in human's life in all aspects. The government's laws in this regard affected the lifestyle of all people. Due to this fact studying about the sentiment of individuals is important to be aware of the future impacts of the coming pandemics. To contribute to this aim, we proposed a NLP (Natural Language Processing) model to analyze open-text answers in a survey in Persian and detect positive and negative feelings of the people in Iran. In this study, a distilBert transformer model was applied to take on this task. We deployed three approaches to perform comparison, and our best model could gain accuracy: 0.824, Precision: 0.824, Recall: 0.798 and F1score: 0.804.

Post-hoc explanation methods are used with the intent of providing insights about neural networks and are sometimes said to help engender trust in their outputs. However, popular explanations methods have been found to be fragile to minor perturbations of input features or model parameters. Relying on constraint relaxation techniques from non-convex optimization, we develop a method that upper-bounds the largest change an adversary can make to a gradient-based explanation via bounded manipulation of either the input features or model parameters. By propagating a compact input or parameter set as symbolic intervals through the forwards and backwards computations of the neural network we can formally certify the robustness of gradient-based explanations. Our bounds are differentiable, hence we can incorporate provable explanation robustness into neural network training. Empirically, our method surpasses the robustness provided by previous heuristic approaches. We find that our training method is the only method able to learn neural networks with certificates of explanation robustness across all six datasets tested.

Federated learning (FL) enables distributed model training from local data collected by users. In distributed systems with constrained resources and potentially high dynamics, e.g., mobile edge networks, the efficiency of FL is an important problem. Existing works have separately considered different configurations to make FL more efficient, such as infrequent transmission of model updates, client subsampling, and compression of update vectors. However, an important open problem is how to jointly apply and tune these control knobs in a single FL algorithm, to achieve the best performance by allowing a high degree of freedom in control decisions. In this paper, we address this problem and propose FlexFL - an FL algorithm with multiple options that can be adjusted flexibly. Our FlexFL algorithm allows both arbitrary rates of local computation at clients and arbitrary amounts of communication between clients and the server, making both the computation and communication resource consumption adjustable. We prove a convergence upper bound of this algorithm. Based on this result, we further propose a stochastic optimization formulation and algorithm to determine the control decisions that (approximately) minimize the convergence bound, while conforming to constraints related to resource consumption. The advantage of our approach is also verified using experiments.

Quantum computers offer the potential of achieving significant speedup for certain computational problems. Yet, many existing quantum algorithms with notable asymptotic speedups require a degree of fault tolerance that is currently unavailable. The quantum algorithm for topological data analysis (TDA) by Lloyd et al. is believed to be one such algorithm. TDA is a powerful technique for extracting complex and valuable shape-related summaries of high-dimensional data. However, the computational demands of classical TDA algorithms are exorbitant, and become impractical for high-order characteristics. In this paper, we present NISQ-TDA, the first fully implemented end-to-end quantum machine learning algorithm needing only a short circuit-depth, that is applicable to non-handcrafted high-dimensional classical data, and with provable asymptotic speedup for certain classes of problems. The algorithm neither suffers from the data-loading problem nor does it need to store the input data on the quantum computer explicitly. Our approach includes three key innovations: an efficient realization of the full boundary operator; a quantum rejection sampling and projection approach to restrict a quantum state to the simplices of the desired order in the given complex; and a stochastic rank estimation method to estimate the topological features in the form of approximate Betti numbers. We present theoretical results that establish additive error guarantees, along with computational cost and circuit-depth complexities for normalized output estimates, up to the error tolerance. The algorithm was successfully executed on quantum computing devices, as well as on noisy quantum simulators, applied to small datasets. Preliminary empirical results suggest that the algorithm is robust to noise. Finally, we provide target depths and noise level estimates to realize near-term, non-fault-tolerant quantum advantage.

In principle, applying variational autoencoders (VAEs) to sequential data offers a method for controlled sequence generation, manipulation, and structured representation learning. However, training sequence VAEs is challenging: autoregressive decoders can often explain the data without utilizing the latent space, known as posterior collapse. To mitigate this, state-of-the-art models'weaken' the'powerful' decoder by applying uniformly random dropout to the decoder input. We show theoretically that this removes pointwise mutual information provided by the decoder input, which is compensated for by utilizing the latent space. We then propose an adversarial training strategy to achieve information-based stochastic dropout. Compared to uniform dropout on standard text benchmark datasets, our targeted approach increases both sequence modeling performance and the information captured in the latent space.

The debate over whether artificial intelligence is good or bad for humanity is one that has been ongoing since the inception of AI itself. On one side, proponents argue that AI can help us to solve some of the world's most pressing problems, such as climate change, disease and poverty. On the other side, detractors claim that AI will eventually surpass human intelligence, leading to a future in which machines rule the world. So far, there is no clear answer as to which side is right. However, what is certain is that AI presents both risks and opportunities for humanity.

Former NASA astronaut Mike Massimino explains NASA's DART mission and why they intentionally crashed a spacecraft into an asteroid A coolant leak detected from the aft end of the Russian space capsule docked to the International Space Station was likely caused by a micrometeorite strike, according to a Russian space official. Sergei Krikalev, a veteran cosmonaut who serves as the director of crewed space flight programs at Roscosmos, said Thursday that a meteorite striking one of the radiators of the Soyuz MS-22 capsule could have caused the coolant to escape. Krikalev said in a statement that the malfunction could affect the performance of the capsule's coolant system and the temperature in the equipment section of the capsule. Roscosmos and NASA have both said that the incident had not posed any danger to the station's crew. "There have been no other changes in parameters on the Soyuz spacecraft and the station, so there is no threat for the crew," he said.

The use of artificial intelligence (AI) has become increasingly common in many different industries and fields, from healthcare to finance to transportation. While the potential benefits of AI are vast and numerous, it's important to also consider the potential drawbacks and negative uses of this technology. One area where AI is increasingly being utilized is in the realm of cybercrime. One way that AI is used in cybercrime is through the development of sophisticated malware. This type of software is designed to infect a computer or network without the user's knowledge and can cause significant damage or disruption.

The Biden administration on Thursday added 36 companies and organizations, including a major Chinese chip maker, to a so-called entity list that will severely restrict their access to certain products, software and technologies. The action, which is aimed at further stymieing China's efforts to develop advanced semiconductors, is the latest step in the Biden administration's campaign to clamp down on China's access to technologies that could be used for military purposes. Administration officials say that China has increasingly blurred the lines between its military and civilian industries, prompting the United States to place restrictions on doing business with Chinese companies that may feed into Beijing's military ambitions. In October, the administration announced sweeping limits on semiconductor exports to China, both from companies within the United States and in other countries that use American technology to make those products. "Today we are building on the actions we took in October to protect U.S. national security by severely restricting the PRC's ability to leverage artificial intelligence, advanced computing, and other powerful, commercially available technologies for military modernization and human rights abuses," Alan Estevez, the under secretary of commerce for industry and security, said in a statement, referring to the People's Republic of China.

This year, we've seen the introduction of powerful generative AI systems that have the ability to create images and text on demand. At the same time, regulators are on the move. Europe is in the middle of finalizing its AI regulation (the AI Act), which aims to put strict rules on high-risk AI systems. Canada, the UK, the US, and China have all introduced their own approaches to regulating high-impact AI. But general-purpose AI seems to be an afterthought rather than the core focus.