This paper proposes a novel method of classifying malware into families using high-resolution greyscale images and multiple instance learning to overcome adversarial binary enlargement. Current methods of visualisation-based malware classification largely rely on lossy transformations of inputs such as resizing to handle the large, variable-sized images. Through empirical analysis and experimentation, it is shown that these approaches cause crucial information loss that can be exploited. The proposed solution divides the images into patches and uses embedding-based multiple instance learning with a convolutional neural network and an attention aggregation function for classification. The implementation is evaluated on the Microsoft Malware Classification dataset and achieves accuracies of up to $96.6\%$ on adversarially enlarged samples compared to the baseline of $22.8\%$. The Python code is available online at https://github.com/timppeters/MIL-Malware-Images .

Policy-Space Response Oracles (PSRO) is an influential algorithm framework for approximating a Nash Equilibrium (NE) in multi-agent non-transitive games. Many previous studies have been trying to promote policy diversity in PSRO. A major weakness in existing diversity metrics is that a more diverse (according to their diversity metrics) population does not necessarily mean (as we proved in the paper) a better approximation to a NE. To alleviate this problem, we propose a new diversity metric, the improvement of which guarantees a better approximation to a NE. Meanwhile, we develop a practical and well-justified method to optimize our diversity metric using only state-action samples. By incorporating our diversity regularization into the best response solving in PSRO, we obtain a new PSRO variant, Policy Space Diversity PSRO (PSD-PSRO). We present the convergence property of PSD-PSRO. Empirically, extensive experiments on various games demonstrate that PSD-PSRO is more effective in producing significantly less exploitable policies than state-of-the-art PSRO variants.

Prevention is better than cure. This old truth applies not only to the prevention of diseases but also to the prevention of issues with AI models used in medicine. The source of malfunctioning of predictive models often lies not in the training process but reaches the data acquisition phase or design of the experiment phase. In this paper, we analyze in detail a single use case - a Kaggle competition related to the detection of abnormalities in X-ray lung images. We demonstrate how a series of simple tests for data imbalance exposes faults in the data acquisition and annotation process. Complex models are able to learn such artifacts and it is difficult to remove this bias during or after the training. Errors made at the data collection stage make it difficult to validate the model correctly. Based on this use case, we show how to monitor data and model balance (fairness) throughout the life cycle of a predictive model, from data acquisition to parity analysis of model scores.

Multiple networks are constructed as S (T 2), M (T 4), and L (T 6) from the original DBPN. In the feature extraction, we use conv(3, 128) followed by conv(1, 32). Then, we use conv(1, 1) for the reconstruction. The input and output images are luminance only. The S network gives a higher PSNR than VDSR, DRCN, and LapSRN.

With our latest developments in machine learning and image recognition, we've implemented automatic face refinement in Gigapixel AI to offer you more powerful and accurate face enlargement. You'll see a toggle in the right panel to enable/disable the new Face Refinement feature. Face Refinement will detect very small faces (16 16 px to 64 64 px) and apply targeted, improved upsampling through machine learning. Ordinarily, faces this small in dimension can be very difficult to upscale, leaving them vulnerable to unpredictable results during enlargement. With our latest improvement, Gigapixel AI produces a more seamless enlargement of faces within your photos, so you'll be satisfied with more natural-looking results!

Today, only about 10% of 7B population in the world have access to good healthcare service, and half of the world don't even access to essential health services. Even among the developed countries, healthcare system is under strain, with rising cost and long wait time. To train up enough physicians and care providers for the growing demands within a short period of time is impractical, if not impossible. The solution has to involve technological breakthroughs. And that's where Machine Learning (ML) and Artificial Intelligence (AI) can make a big impact.

An algorithm that's able to accurately predict autism diagnoses in young kids could enable potental interventions to be made earlier. A team of researchers at the University of North Carolina at Chapel Hill have developed a deep learning algorithm that can accurately predict whether a child at high risk of autism is likely to be diagnosed with the disorder in early childhood. The algorithm was able to predict with 81 percent accuracy whether a diagnosis of autism would be made for a child with an autistic sibling,. The deep learning tool was developed in conjunction with computer scientists from the College of Charleston as part of the Infant Brain Imaging Study, which focuses on early brain development among children with autism. By scanning their brains at 6 months old, a year old, and 2 years old, they were able to make some interesting discoveries.