Abstract: Despite a rapid rise in the quality of built-in smartphone cameras, their physical limitations - small sensor size, compact lenses and the lack of specific hardware, - impede them to achieve the quality results of DSLR cameras. In this work we present an end-to-end deep learning approach that bridges this gap by translating ordinary photos into DSLR-quality images. We propose learning the translation function using a residual convolutional neural network that improves both color rendition and image sharpness. Since the standard mean squared loss is not well suited for measuring perceptual image quality, we introduce a composite perceptual error function that combines content, color and texture losses. The first two losses are defined analytically, while the texture loss is learned in an adversarial fashion.

For Ben Treynor Sloss, Google's VP of engineering, the data centre of the future will not only benefit from the use of machine learning, but will be run by AI. Sloss pointed to the significant cost savings gleaned from Google's own DeepMind machine learning system which was instrumental in running the technology giant's data centre in 2016. The DeepMind system was able to significantly improve the power efficiency of the data centre by adjusting how servers were run and the operation of power and cooling equipment. Energy reductions reached 40% and if similar systems were rolled out across all Google's data centres globally, it could add up to a saving of tens of millions of dollars each year. For Alex Robbio, co-founder and president of Belatrix Software, the potential for the application of machine learning and Artificial Intelligence is about more than just power management.

A data science conference by Analytics Vidhya that brings together the finest data scientists from across the country & globe. Join us from 9 – 11 November and see live action in Advanced Analytics, Artificial Intelligence, Machine Learning & Deep Learning. This is a unique opportunity to listen to amazing speakers, network with them and attend rigorous workshops. DataHack Summit 2017 will talk about new developments in the field of analytics and machine learning. It's a 3-days gathering of chief data scientists, advanced professionals, researchers, analysts, technology evangelists, data science experts data hackers and practitioners.

When you think of artificial intelligence, the field of botany probably isn't uppermost in your mind. When you picture settings for cutting-edge computational research, century-old museums may not top the list. And yet, a just-published article in the Biodiversity Data Journal shows that some of the most exciting and portentous innovation in machine learning is taking place at none other than the National Herbarium of the National Museum of Natural History in Washington, D.C. The paper, which demonstrates that digital neural networks are capable of distinguishing between two similar families of plants with rates of accuracy well over 90 percent, implies all sorts of mouth-watering possibilities for scientists and academics going forward. The study relies on software grounded in "deep learning" algorithms, which allow computer programs to accrue experience in much the same way human experts do, upping their game each time they run.

There are so many new models and architectures. If you find something interesting and worth paying attention to, please send us a pull requests (PR) and write issues. Please send PRs on the Neural Net Arch Genealogy.txt Please send a PR on the Neural Net Arch Genealogy.txt Your pull requests and issues are always welcome.

Artificial Intelligence: This "umbrella" term encompasses all these areas of research. According to field experts, the definition of AI has suffered many detours, thus rendering the term nearly useless over the years. McKinsey's 2015 Report titled Disruptive technologies: Advances that will transform life, business, and the global economy suggests that about 12 disruptive technologies will create a great global impact 10 years from now. Among these 12, at least five have been determined to be related to AI and Robotics, which includes: automated "knowledge" tasks, Robotics, Internet of Things, 3D Printing technology, and self-driving cars. The total economic impact of these combined technologies has been estimated to reach between $50-99.5 trillion by 2025!

HPE Rapid Software Installation for AI: HPE introduced an integrated hardware and software solution, purpose-built for high performance computing and deep learning applications. Based on the HPE Apollo 6500 system in collaboration with Bright Computing to enable rapid deep learning application development, this solution includes pre-configured deep learning software frameworks, libraries, automated software updates and cluster management optimized for deep learning and supports NVIDIA Tesla V100 GPUs. HPE Deep Learning Cookbook: Built by the AI Research team at Hewlett Packard Labs, the deep learning cookbook is a set of tools to guide customers in selecting the best hardware and software environment for different deep learning tasks. These tools help enterprises estimate performance of various hardware platforms, characterize the most popular deep learning frameworks, and select the ideal hardware and software stacks to fit their individual needs. The Deep Learning Cookbook can also be used to validate the performance and tune the configuration of already purchased hardware and software stacks.

In this paper, we consider parameter recovery for non-overlapping convolutional neural networks (CNNs) with multiple kernels. We show that when the inputs follow Gaussian distribution and the sample size is sufficiently large, the squared loss of such CNNs is $\mathit{~locally~strongly~convex}$ in a basin of attraction near the global optima for most popular activation functions, like ReLU, Leaky ReLU, Squared ReLU, Sigmoid and Tanh. The required sample complexity is proportional to the dimension of the input and polynomial in the number of kernels and a condition number of the parameters. We also show that tensor methods are able to initialize the parameters to the local strong convex region. Hence, for most smooth activations, gradient descent following tensor initialization is guaranteed to converge to the global optimal with time that is linear in input dimension, logarithmic in precision and polynomial in other factors. To the best of our knowledge, this is the first work that provides recovery guarantees for CNNs with multiple kernels under polynomial sample and computational complexities.

Motivated by the resurgence of neural networks in being able to solve complex learning tasks we undertake a study of high depth networks using ReLU gates which implement the function $x \mapsto \max\{0,x\}$. We try to understand the role of depth in such neural networks by showing size lowerbounds against such network architectures in parameter regimes hitherto unexplored. In particular we show the following two main results about neural nets computing Boolean functions of input dimension $n$, 1. We use the method of random restrictions to show almost linear, $\Omega(\epsilon^{2(1-\delta)}n^{1-\delta})$, lower bound for completely weight unrestricted LTF-of-ReLU circuits to match the Andreev function on at least $\frac{1}{2} +\epsilon$ fraction of the inputs for $\epsilon > \sqrt{2\frac{\log^{\frac {2}{2-\delta}}(n)}{n}}$ for any $\delta \in (0,\frac 1 2)$ 2. We use the method of sign-rank to show exponential in dimension lower bounds for ReLU circuits ending in a LTF gate and of depths upto $O(n^{\xi})$ with $\xi < \frac{1}{8}$ with some restrictions on the weights in the bottom most layer. All other weights in these circuits are kept unrestricted. This in turns also implies the same lowerbounds for LTF circuits with the same architecture and the same weight restrictions on their bottom most layer. Along the way we also show that there exists a $\mathbb{R}^ n\rightarrow \mathbb{R}$ Sum-of-ReLU-of-ReLU function which Sum-of-ReLU neural nets can never represent no matter how large they are allowed to be.

Power grids are one of the most important components of infrastructure in today's world. Every nation is dependent on the security and stability of its own power grid to provide electricity to the households and industries. A malfunction of even a small part of a power grid can cause loss of productivity, revenue and in some cases even life. Thus, it is imperative to design a system which can detect the health of the power grid and take protective measures accordingly even before a serious anomaly takes place. To achieve this objective, we have set out to create an artificially intelligent system which can analyze the grid information at any given time and determine the health of the grid through the usage of sophisticated formal models and novel machine learning techniques like recurrent neural networks. Our system simulates grid conditions including stimuli like faults, generator output fluctuations, load fluctuations using Siemens PSS/E software and this data is trained using various classifiers like SVM, LSTM and subsequently tested. The results are excellent with our methods giving very high accuracy for the data. This model can easily be scaled to handle larger and more complex grid architectures.