While domain adaptation has been actively researched in recent years, most theoretical results and algorithms focus on the single-source-single-target adaptation setting. Naive application of such algorithms on multiple source domain adaptation problem may lead to suboptimal solutions. As a step toward bridging the gap, we propose a new generalization bound for domain adaptation when there are multiple source domains with labeled instances and one target domain with unlabeled instances. Compared with existing bounds, the new bound does not require expert knowledge about the target distribution, nor the optimal combination rule for multisource domains. Interestingly, our theory also leads to an efficient learning strategy using adversarial neural networks: we show how to interpret it as learning feature representations that are invariant to the multiple domain shifts while still being discriminative for the learning task. To this end, we propose two models, both of which we call multisource domain adversarial networks (MDANs): the first model optimizes directly our bound, while the second model is a smoothed approximation of the first one, leading to a more data-efficient and task-adaptive model. The optimization tasks of both models are minimax saddle point problems that can be optimized by adversarial training. To demonstrate the effectiveness of MDANs, we conduct extensive experiments showing superior adaptation performance on three real-world datasets: sentiment analysis, digit classification, and vehicle counting.

We propose a probabilistic framework for domain adaptation that blends both generative and discriminative modeling in a principled way. Under this framework, generative and discriminative models correspond to specific choices of the prior over parameters. This provides us a very general way to interpolate between generative and discriminative extremes through different choices of priors. By maximizing both the marginal and the conditional log-likelihoods, models derived from this framework can use both labeled instances from the source domain as well as unlabeled instances from both source and target domains. Under this framework, we show that the popular reconstruction loss of autoencoder corresponds to an upper bound of the negative marginal log-likelihoods of unlabeled instances, where marginal distributions are given by proper kernel density estimations. This provides a way to interpret the empirical success of autoencoders in domain adaptation and semi-supervised learning. We instantiate our framework using neural networks, and build a concrete model, DAuto. Empirically, we demonstrate the effectiveness of DAuto on text, image and speech datasets, showing that it outperforms related competitors when domain adaptation is possible.

The Keras Python library makes creating deep learning models fast and easy. The sequential API allows you to create models layer-by-layer for most problems. It is limited in that it does not allow you to create models that share layers or have multiple inputs or outputs. The functional API in Keras is an alternate way of creating models that offers a lot more flexibility, including creating more complex models. In this tutorial, you will discover how to use the more flexible functional API in Keras to define deep learning models.

Yann LeCun is one of AI's most accomplished minds, so when he says that even recent advances in the field aren't taking us closer to super-intelligent machines, you need to pay attention. LeCun has been working in AI for decades, and is one of the co-creators of convolutional neural networks -- a type of program that's proved particularly adept at analyzing visual data, and powers everything from self-driving cars to facial recognition. Now, as head of Facebook's AI research facility FAIR, he helps AI make the journey from the lab to the real world. His team's software automatically captions photos for blind users and performs 4.5 billion AI-powered translations a day. "We had a bigger impact on products than Mark Zuckerberg expected," LeCun told The Verge over Skype recently.

Since its founding by Elon Musk and others nearly two years ago, nonprofit research lab OpenAI has published dozens of research papers. One posted online Thursday is different: Its lead author is still in high school. The wunderkind is Kevin Frans, a senior currently working on his college applications. He trained his first neural net--the kind of system that tech giants use to recognize your voice or face--two years ago, at the age of 15. Inspired by reports of software mastering Atari games and the board game Go, he has since been reading research papers and building pieces of what they described.

It's odd that the search engine company known as the "Google of China" says that its open-source autonomous driving platform Apollo is the "Android of the auto industry." But that's exactly what Baidu is trying to be with Apollo and it's racking up partners worldwide (including Ford, Daimler, NVIDIA and others) to make it a reality. At an event in Sunnyvale, California, the search company unveiled Apollo 1.5, its latest version of its autonomous driving platform. The new version supports HD maps, LiDAR, obstacle detection and deep learning technologies. All of which, like the rest of the platform, is open source and modular so developers can pick and choose what they want to use in their own systems. At some point a developer will have to contribute to the platform to access more of the data for their own needs.

Finding stuff you actually want to buy on eBay is getting a whole lot easier thanks to the online shopping site's new Image Search function. Instead of trying every possible search term combination to come up with the exact thing you want, you can now simply upload a photo (Image Search) or click "Find It On eBay" when browsing another website, and the eBay app will surface relevant listings. Find It On eBay is now live on Android, while Image Search is live on both Android and iOS. The feature uses a deep learning model called a convolutional neural network, which sorts through eBay's billion listings to find items based on visual similarity. And as shoppers continue to search with pictures, it gets smarter, improving the results it returns, meaning you'll no longer have to ask strangers where they got their shoes from -- you can just snap a covert picture instead.

Artificial Intelligence is already outsmarting us at '80s computer games by finding ways to beat games that developers didn't even know were there. Just wait until it figures out how to beat us in ways that matter. Max Tegmark: I define intelligence simply as how good something is at accomplishing complex goals. Human intelligence today is very different from machine intelligence today in multiple ways. First of all, machine intelligence in the past used to be just an always inferior to human intelligence.