The progressive growing generative adversarial network is an approach for training a deep convolutional neural network model for generating synthetic images. It is an extension of the more traditional GAN architecture that involves incrementally growing the size of the generated image during training, starting with a very small image, such as a 4 4 pixels. This allows the stable training and growth of GAN models capable of generating very large high-quality images, such as images of synthetic celebrity faces with the size of 1024 1024 pixels. In this tutorial, you will discover how to develop progressive growing generative adversarial network models from scratch with Keras. Discover how to develop DCGANs, conditional GANs, Pix2Pix, CycleGANs, and more with Keras in my new GANs book, with 29 step-by-step tutorials and full source code. How to Implement Progressive Growing GAN Models in Keras Photo by Diogo Santos Silva, some rights reserved. GANs are effective at generating crisp synthetic images, although are typically limited in the size of the images that can be generated.

Object detection is a computer vision technique whose aim is to detect objects such as cars, buildings, and human beings, just to mention a few. The objects can generally be identified from either pictures or video feeds. Object detection has been applied widely in video surveillance, self-driving cars, and object/people tracking. In this piece, we'll look at the basics of object detection and review some of the most commonly-used algorithms and a few brand new approaches, as well. Object detection locates the presence of an object in an image and draws a bounding box around that object.

Alphabet's DeepMind lost $572 million last year. DeepMind, likely the world's largest research-focused artificial intelligence operation, is losing a lot of money fast, more than $1 billion in the past three years. DeepMind also has more than $1 billion in debt due in the next 12 months. Does this mean that AI is falling apart? Gary Marcus is founder and CEO of Robust.AI and a professor of psychology and neural science at NYU.

The expanding universe of artificial intelligence includes many terms and technologies. That naturally leads to overlap and confusion. AI and machine learning are mentioned together so often that some people – non-technical folks especially – might think they're one and the same. They're related but not actually interchangeable terms: Machine learning is a subset, or a specific discipline, of AI. Start adding other terms and technologies into the mix – deep learning is yet another subset of machine learning, for instance – and the opportunities abound for further misconceptions. Deciphering the differences between terms and technologies takes a twist with robotic process automation (RPA) and AI.

Road Watch 2.0 Vision Zero Pedestrian Deaths Project: Learn how an award-winning Richmond Hill and York Regional Police road safety Road Watch program is the base for a space age approach to make Toronto roads safer, as kicked off on the Global News 640 AM John Oakley Show. Hear a plan to make roads safer while mitigating climate through earth and Space LiDAR technology. Learn how road safety and climate change mitigation is combined in the Ethical AI Energy Cloud City master plan, a UN 17 Sustainable Development Goals Emerging Technology Framework to Unite Society. Dave D'Silva founded Intelligent Market Solutions Group (IMSG) to make good on a University of Waterloo pact with Bill Gates. IMSG is a socio-economic emerging technology project management firm creating Star Trek inspired Ethical AI systems.

State-of-the-art machine learning frameworks support a wide variety of design features to enable a flexible machine learning programming interface and to ease the programmability burden on machine learning developers. Identifying and using a performance-optimal setting in feature-rich frameworks, however, involves a non-trivial amount of performance characterization and domain-specific knowledge. This paper takes a deep dive into analyzing the performance impact of key design features and the role of parallelism. The observations and insights distill into a simple set of guidelines that one can use to achieve much higher training and inference speedup. The evaluation results show that our proposed performance tuning guidelines outperform both the Intel and TensorFlow recommended settings by 1.29x and 1.34x, respectively, across a diverse set of real-world deep learning models.

Podcasts have emerged as an important medium to share information through. Though not as popular as the video, there are tons of very interesting podcasts that are being produced regularly. So, we decided to hand-curate a list of interesting and popular podcasts around the topic of AI and machine learning. Talking Machines is your window into the world of machine learning. Your hosts, Katherine Gorman and Neil Lawrence, bring you clear conversations with experts in the field, insightful discussions of industry news, and useful answers to your questions.

Like yesterday, we bring you the best tweets covering major talks and events at IJCAI 2019. Follow the invited talk by @MichelaMilano1 at @IJCAIconf "Empirical Model Learning: merging knowledge-based and data-driven decision models through machine learning" https://t.co/FA7gR0105H Interesting idea to use deep forest ensembles as alternative to deep neural networks. Introducing the #AIglassbox: @RecklessCoding presents our paper at #ijcai2019. This takes place in 10 minutes!

A deep-learning-based surrogate model is developed and applied for predicting dynamic subsurface flow in channelized geological models. The surrogate model is based on deep convolutional and recurrent neural network architectures, specifically a residual U-Net and a convolutional long short term memory recurrent network. Training samples entail global pressure and saturation maps, at a series of time steps, generated by simulating oil-water flow in many (1500 in our case) realizations of a 2D channelized system. After training, the `recurrent R-U-Net' surrogate model is shown to be capable of accurately predicting dynamic pressure and saturation maps and well rates (e.g., time-varying oil and water rates at production wells) for new geological realizations. Assessments demonstrating high surrogate-model accuracy are presented for an individual geological realization and for an ensemble of 500 test geomodels. The surrogate model is then used for the challenging problem of data assimilation (history matching) in a channelized system. For this study, posterior reservoir models are generated using the randomized maximum likelihood method, with the permeability field represented using the recently developed CNN-PCA parameterization. The flow responses required during the data assimilation procedure are provided by the recurrent R-U-Net. The overall approach is shown to lead to substantial reduction in prediction uncertainty. High-fidelity numerical simulation results for the posterior geomodels (generated by the surrogate-based data assimilation procedure) are shown to be in essential agreement with the recurrent R-U-Net predictions. The accuracy and dramatic speedup provided by the surrogate model suggest that it may eventually enable the application of more formal posterior sampling methods in realistic problems.

Traditional anatomical analyses captured only a fraction of real phenomic information. Here, we apply deep learning to quantify total phenotypic similarity across 2468 butterfly photographs, covering 38 subspecies from the polymorphic mimicry complex of $\textit{Heliconius erato}$ and $\textit{Heliconius melpomene}$. Euclidean phenotypic distances, calculated using a deep convolutional triplet network, demonstrate significant convergence between interspecies co-mimics. This quantitatively validates a key prediction of M\"ullerian mimicry theory, evolutionary biology's oldest mathematical model. Phenotypic neighbor-joining trees are significantly correlated with wing pattern gene phylogenies, demonstrating objective, phylogenetically informative phenome capture. Comparative analyses indicate frequency-dependent, mutual convergence with coevolutionary exchange of wing pattern features. Therefore, phenotypic analysis supports reciprocal coevolution, predicted by classical mimicry theory but since disputed, and reveals mutual convergence as an intrinsic generator for the surprising diversity of M\"ullerian mimicry. This demonstrates that deep learning can generate phenomic spatial embeddings which enable quantitative tests of evolutionary hypotheses previously only testable subjectively.