Neural Architecture Search has recently shown potential to automate the design of Neural Networks. The use of Neural Network agents trained with Reinforcement Learning can offer the possibility to learn complex architectural patterns, as well as the ability to explore a vast and compositional search space. On the other hand, evolutionary algorithms offer the sample efficiency needed for such a resource intensive application. We propose a class of Evolutionary-Neural hybrid agents (Evo-NAS), that retain the qualities of the two approaches. We show that the Evo-NAS agent outperforms both Neural and Evolutionary agents when applied to architecture search for a suite of text classification and image classification benchmarks. On a high-complexity architecture search space for image classification, the Evo-NAS agent surpasses the performance of commonly used agents with only 1/3 of the trials.

Recent developments in the field of deep learning have motivated many researchers to apply these methods to problems in quantum information. Torlai and Melko first proposed a decoder for surface codes based on neural networks. Since then, many other researchers have applied neural networks to study a variety of problems in the context of decoding. An important development in this regard was due to Varsamopoulos et al. who proposed a two-step decoder using neural networks. Subsequent work of Maskara et al. used the same concept for decoding for various noise models. We propose a similar two-step neural decoder using inverse parity-check matrix for topological color codes. We show that it outperforms the state-of-the-art performance of non-neural decoders for independent Pauli errors noise model on a 2D hexagonal color code. Our final decoder is independent of the noise model and achieves a threshold of $10 \%$. Our result is comparable to the recent work on neural decoder for quantum error correction by Maskara et al.. It appears that our decoder has significant advantages with respect to training cost and complexity of the network for higher lengths when compared to that of Maskara et al.. Our proposed method can also be extended to arbitrary dimension and other stabilizer codes.

As the foundation of driverless vehicle and intelligent robots, Simultaneous Localization and Mapping(SLAM) has attracted much attention these days. However, non-geometric modules of traditional SLAM algorithms are limited by data association tasks and have become a bottleneck preventing the development of SLAM. To deal with such problems, many researchers seek to Deep Learning for help. But most of these studies are limited to virtual datasets or specific environments, and even sacrifice efficiency for accuracy. Thus, they are not practical enough. We propose DF-SLAM system that uses deep local feature descriptors obtained by the neural network as a substitute for traditional hand-made features. Experimental results demonstrate its improvements in efficiency and stability. DF-SLAM outperforms popular traditional SLAM systems in various scenes, including challenging scenes with intense illumination changes. Its versatility and mobility fit well into the need for exploring new environments. Since we adopt a shallow network to extract local descriptors and remain others the same as original SLAM systems, our DF-SLAM can still run in real-time on GPU.

Discrete-action algorithms have been central to numerous recent successes of deep reinforcement learning. However, applying these algorithms to high-dimensional action tasks requires tackling the combinatorial increase of the number of possible actions with the number of action dimensions. This problem is further exacerbated for continuous-action tasks that require fine control of actions via discretization. In this paper, we propose a novel neural architecture featuring a shared decision module followed by several network branches, one for each action dimension. This approach achieves a linear increase of the number of network outputs with the number of degrees of freedom by allowing a level of independence for each individual action dimension. To illustrate the approach, we present a novel agent, called Branching Dueling Q-Network (BDQ), as a branching variant of the Dueling Double Deep Q-Network (Dueling DDQN). We evaluate the performance of our agent on a set of challenging continuous control tasks. The empirical results show that the proposed agent scales gracefully to environments with increasing action dimensionality and indicate the significance of the shared decision module in coordination of the distributed action branches. Furthermore, we show that the proposed agent performs competitively against a state-of-the-art continuous control algorithm, Deep Deterministic Policy Gradient (DDPG).

Intel today announced the open source release of Nauta, a platform for deep learning distributed across multiple servers using Kubernetes or Docker. The platform can operate with a number of popular machine learning frameworks such as MXNet, TensorFlow, and PyTorch, and uses processing systems that can work with a cluster of Intel's Xeon CPUs. Results of deep learning experiments conducted with Nauta can be seen using TensorBoard, command line code, or a Nauta web user interface. "Nauta is an enterprise-grade stack for teams who need to run DL workloads to train models that will be deployed in production. With Nauta, users can define and schedule containerized deep learning experiments using Kubernetes on single or multiple worker nodes, and check the status and results of those experiments to further adjust and run additional experiments, or prepare the trained model for deployment," according to a blog post announcing the news today.

In this tutorial, you will learn how to perform regression using Keras and Deep Learning. You will learn how to train a Keras neural network for regression and continuous value prediction, specifically in the context of house price prediction. Today's post kicks off a 3-part series on deep learning, regression, and continuous value prediction. We'll be studying Keras regression prediction in the context of house price prediction: Unlike classification (which predicts labels), regression enables us to predict continuous values. For example, classification may be able to predict one of the following values: {cheap, affordable, expensive}.

When we last checked in with DeepMind, Oriol Vinyals stepped on to the BlizzCon 2018 stage to share the exciting progress their AI had made in StarCraft II. The AI, or agent, was able to perform basic macro focused strategies as well as defend against cheesy tactics like cannon rushes. It's only been a few months since BlizzCon but DeepMind is ready to share more information on their research. The StarCraft games have emerged as a "grand challenge" for the AI community as they're the perfect environment for benchmarking progress against problems such as planning, dealing with uncertainty and spatial reasoning. On January 24, at 19:00 CET, head over to StarCraft's Twitch channel or DeepMind's Youtube channel to learn what developments have been made.

Manning has teamed up with Deep Learning and the Game of Go authors Max Pumperla and Kevin Ferguson and Online Go Server (OGS) to host the first-ever Manning Go Bot Tournament. Pit your bot against other like-minded masters and maybe even take home some great prizes! Building an AI agent to play the ancient strategy game of Go against other bots is a fantastic way to sharpen your deep learning skills. Plus, it's fun to find out how your Go bot stacks up against the competition. Here's how to enter, play, and win!

The much-ballyhooed artificial intelligence approach boasts impressive feats but still falls short of human brainpower. Researchers are determined to figure out what's missing. Yet the artificial intelligence (AI) identifies it as a toaster, even though it was trained with the same powerful and oft-publicized deep-learning techniques that have produced a white-hot revolution in driverless cars, speech understanding, and a multitude of other AI applications. That means the AI was shown several thousand photos of bananas, slugs, snails, and similar-looking objects, like so many flash cards, and then drilled on the answers until it had the classification down cold. And yet this advanced system was quite easily confused--all it took was a little day-glow sticker, digitally pasted in one corner of the image.

Startup UiPath Offers Teams of AI Assistants to Help Manage Tedious Back Office Work. AI can now help you get a leg up on tedious office work. Just ask Param Kahlon, who is developing teams of bots that can make life easier in the workplace. Kahlon is chief product officer at UiPath, a pioneer in robotic process automation (RPA) software, which helps humans work with machines to automate aging software workflows. Now, AI-powered software bots can open these applications and handle it all.