Estimation of intrinsic images still remains a challenging task due to weaknesses of ground-truth datasets, which either are too small or present non-realistic issues. On the other hand, end-to-end deep learning architectures start to achieve interesting results that we believe could be improved if important physical hints were not ignored. In this work, we present a twofold framework: (a) a flexible generation of images overcoming some classical dataset problems such as larger size jointly with coherent lighting appearance; and (b) a flexible architecture tying physical properties through intrinsic losses. Our proposal is versatile, presents low computation time, and achieves state-of-the-art results.

Cross-Domain Recommendation (CDR) and Cross-System Recommendations (CSR) are two of the promising solutions to address the long-standing data sparsity problem in recommender systems. They leverage the relatively richer information, e.g., ratings, from the source domain or system to improve the recommendation accuracy in the target domain or system. Therefore, finding an accurate mapping of the latent factors across domains or systems is crucial to enhancing recommendation accuracy. However, this is a very challenging task because of the complex relationships between the latent factors of the source and target domains or systems. To this end, in this paper, we propose a Deep framework for both Cross-Domain and Cross-System Recommendations, called DCDCSR, based on Matrix Factorization (MF) models and a fully connected Deep Neural Network (DNN). Specifically, DCDCSR first employs the MF models to generate user and item latent factors and then employs the DNN to map the latent factors across domains or systems. More importantly, we take into account the rating sparsity degrees of individual users and items in different domains or systems and use them to guide the DNN training process for utilizing the rating data more effectively. Extensive experiments conducted on three real-world datasets demonstrate that DCDCSR framework outperforms the state-of-the-art CDR and CSR approaches in terms of recommendation accuracy.

Detecting manipulations in digital documents is becoming increasingly important for information verification purposes. Due to the proliferation of image editing software, altering key information in documents has become widely accessible. Nearly all approaches in this domain rely on a procedural approach, using carefully generated features and a hand-tuned scoring system, rather than a data-driven and generalizable approach. We frame this issue as a graph comparison problem using the character bounding boxes, and propose a model that leverages graph features using OCR (Optical Character Recognition). Our model relies on a data-driven approach to detect alterations by training a random forest classifier on the graph-based OCR features. We evaluate our algorithm's forgery detection performance on dataset constructed from real business documents with slight forgery imperfections. Our proposed model dramatically outperforms the most closely-related document manipulation detection model on this task.

Remember the robotic prosthetic arm the Rebel fleet replaced Luke Skywalker's hand with after Darth Vader severed it in an epic lightsaber duel in The Empire Strikes Back? Of course you do--and so do scientists. Luke's cybernetic replacement limb was pretty badass, but not exactly replicable in the medical world at the time, or even now. But a team of researchers at the National University of Singapore are hoping to change that with a new kind of artificial nervous system. Think of it as electronic "skin."

An advanced artificial intelligence created by OpenAI, a company founded by genius billionaire Elon Musk, recently penned an op-ed for The Guardian that was so convincingly human many readers were astounded and frightened. Just writing that sentence made me feel like a terrible journalist. That's a really crappy way to start an article about artificial intelligence. The statement contains only trace amounts of truth and is intended to shock you into thinking that what follows will be filled with amazing revelations about a new era of technological wonder. Here's what the lede sentence of an article about the GPT-3 op-ed should look like, as Neural writer Thomas Macaulay handled it earlier this week: The Guardian today published an article purportedly written "entirely" by GPT-3, OpenAI's vaunted language generator.

DUBAI (Reuters) - The United Arab Emirates' Mohamed Bin Zayed University of Artificial Intelligence and Israel's Weizmann Institute of Science have agreed to work together, UAE state news agency WAM said on Sunday. The memorandum of understanding follows the UAE's decision a month ago to normalize relations with Israel. Both countries have said they hope normalised ties will bring economic and technological benefits. The MoU is the first signed between Israeli and UAE higher education bodies, WAM said, intending to "advance the development and use of artificial intelligence as a tool for progress". Spheres of possible collaboration include academic exchanges, conferences, sharing computing resources and the establishment of a joint virtual institute for artificial intelligence, WAM said.

Machine learning accelerates the design of lead-free and stable halide perovskites.

… can also determine the best placements or designs for online ads, and there are deep learning systems that can predict customer churn in business.

Yesterday, Google wrote in a blog post that the company is using Artificial Intelligence and machine learning techniques to more quickly recognize …

Deep learning (DL) has been increasingly adopted by a variety of software-intensive systems.