Researchers at OpenAI have already proven AI can get really good at video games. Now they are teaching AI how to learn games quickly, like a human would. That's why they've challenged developers to submit their own code for an AI-only Sonic the Hedgehog competition. For more videos, subscribe to Mashable Daily: http://on.mash.to/SubscribeNews Give us a follow: Facebook: https://www.facebook.com/mashable/

Imbalanced data with a skewed class distribution are common in many real-world applications. Deep Belief Network (DBN) is a machine learning technique that is effective in classification tasks. However, conventional DBN does not work well for imbalanced data classification because it assumes equal costs for each class. To deal with this problem, cost-sensitive approaches assign different misclassification costs for different classes without disrupting the true data sample distributions. However, due to lack of prior knowledge, the misclassification costs are usually unknown and hard to choose in practice. Moreover, it has not been well studied as to how cost-sensitive learning could improve DBN performance on imbalanced data problems. This paper proposes an evolutionary cost-sensitive deep belief network (ECS-DBN) for imbalanced classification. ECS-DBN uses adaptive differential evolution to optimize the misclassification costs based on training data, that presents an effective approach to incorporating the evaluation measure (i.e. G-mean) into the objective function. We first optimize the misclassification costs, then apply them to deep belief network. Adaptive differential evolution optimization is implemented as the optimization algorithm that automatically updates its corresponding parameters without the need of prior domain knowledge. The experiments have shown that the proposed approach consistently outperforms the state-of-the-art on both benchmark datasets and real-world dataset for fault diagnosis in tool condition monitoring.

To answer questions about racial inequality, we often need a way to infer race and ethnicity from a name. Until now, a bulk of the focus has been on optimally exploiting the last names list provided by the Census Bureau. But there is more information in the first names, especially for African Americans. To estimate the relationship between full names and race, we exploit the Florida voter registration data and the Wikipedia data. In particular, we model the relationship between the sequence of characters in a name, and race and ethnicity using Long Short Term Memory Networks. Our out of sample (OOS) precision and recall for the full name model estimated on the Florida Voter Registration data is .83 and .84 respectively. This compares to OOS precision and recall of .79 and .81 for the last name only model. Commensurate numbers for Wikipedia data are .73 and .73 for the full name model and .66 and .67 for the last name model. To illustrate the use of this method, we apply our method to the campaign finance data to estimate the share of donations made by people of various racial groups.

Deep reinforcement learning has shown its success in game playing. However, 2.5D fighting games would be a challenging task to handle due to ambiguity in visual appearances like height or depth of the characters. Moreover, actions in such games typically involve particular sequential action orders, which also makes the network design very difficult. Based on the network of Asynchronous Advantage Actor-Critic (A3C), we create an OpenAI-gym-like gaming environment with the game of Little Fighter 2 (LF2), and present a novel A3C+ network for learning RL agents. The introduced model includes a Recurrent Info network, which utilizes game-related info features with recurrent layers to observe combo skills for fighting. In the experiments, we consider LF2 in different settings, which successfully demonstrates the use of our proposed model for learning 2.5D fighting games.

According to Facebook, PyTorch 1.0 takes the modular, production-oriented capabilities from Caffe2 and ONNX and combines them with PyTorch's existing flexible, research-focused design to provide a fast, seamless path from research prototyping to production deployment for a broad range of AI projects. The technology in PyTorch 1.0 has already powered many Facebook products and services at scale, including performing 6 billion text translations per day.

In last article I tried to show my vision on what research areas are maturing and can grow big this year. Research is cool, but there must be something from AI world that became mature in 2017 and is ready now to be used in mass applications. This is what this article will be about -- I would like to tell about technologies that are good enough to be used in your current work or to build your own startup based on them. Important note: this is the list of AI areas, algorithms or technologies that are ready to use right now. For example, you can see time series analysis in the list, because deep learning is rapidly replacing previous state of the art in signal processing.

Some recent surveys and predictions show that an increasing number of enterprises are making investments in all forms of AI and there is a growing interest in experimenting with deep learning. I spoke with O'Reilly Media's chief data scientist, Ben Lorica on the state of deep learning in the enterprise to get further insights. "It's a bit early to judge AI," says Ben who believes that many enterprises that have data science and machine learning groups will extend their experimentation and explore deep learning. Deep learning lies at the intersection of big data, big model, and big compute. It requires a large volume of training data and knowledge of how to configure deep learning algorithms.

There were two options for the course project. Students either chose their own topic ("Custom Project"), or took part in a competition to build Question Answering models for the SQuAD challenge ("Default Project"). You can see the in-class SQuAD challenge leaderboard here. The previous year's reports from CS224n 2017 are available here.

Unlike classification where the end result of the very deep network is the only important thing, semantic segmentation not only requires discrimination at pixel level but also a mechanism to project the discriminative features learnt at different stages of the encoder onto the pixel space. Different approaches employ different mechanisms as a part of the decoding mechanism. Let's explore the 3 main approaches: The region-based methods generally follow the "segmentation using recognition" pipeline, which first extracts free-form regions from an image and describes them, followed by region-based classification. At test time, the region-based predictions are transformed to pixel predictions, usually by labeling a pixel according to the highest scoring region that contains it. R-CNN (Regions with CNN feature) is one representative work for the region-based methods.

For today's leading deep learning methods and technology, attend the conference and training workshops at Deep Learning World Las Vegas, June 3-7, 2018. Deep Learning is the newest trend coming out of Machine Learning, but what exactly is it? And how do I learn more? Deep learning is a significant part of what makes up the broader subject of machine learning. Still relatively new, its popularity is constantly growing and so it makes sense that people would want to read and learn more about the subject.