Recognizing facial action units (AUs) from spontaneous facial expressions is still a challenging problem. Most recently, CNNs have shown promise on facial AU recognition. However, the learned CNNs are often overfitted and do not generalize well to unseen subjects due to limited AU-coded training images. We proposed a novel Incremental Boosting CNN (IB-CNN) to integrate boosting into the CNN via an incremental boosting layer that selects discriminative neurons from the lower layer and is incrementally updated on successive mini-batches. In addition, a novel loss function that accounts for errors from both the incremental boosted classifier and individual weak classifiers was proposed to fine-tune the IB-CNN. Experimental results on four benchmark AU databases have demonstrated that the IB-CNN yields significant improvement over the traditional CNN and the boosting CNN without incremental learning, as well as outperforming the state-of-the-art CNN-based methods in AU recognition. The improvement is more impressive for the AUs that have the lowest frequencies in the databases.

We study the problem of synthesizing a number of likely future frames from a single input image. In contrast to traditional methods, which have tackled this problem in a deterministic or non-parametric way, we propose a novel approach which models future frames in a probabilistic manner. Our proposed method is therefore able to synthesize multiple possible next frames using the same model. Solving this challenging problem involves low- and high-level image and motion understanding for successful image synthesis. Here, we propose a novel network structure, namely a Cross Convolutional Network, that encodes images as feature maps and motion information as convolutional kernels to aid in synthesizing future frames. In experiments, our model performs well on both synthetic data, such as 2D shapes and animated game sprites, as well as on real-wold video data. We show that our model can also be applied to tasks such as visual analogy-making, and present analysis of the learned network representations.

A core challenge for an agent learning to interact with the world is to predict how its actions affect objects in its environment. Many existing methods for learning the dynamics of physical interactions require labeled object information. However, to scale real-world interaction learning to a variety of scenes and objects, acquiring labeled data becomes increasingly impractical. To learn about physical object motion without labels, we develop an action-conditioned video prediction model that explicitly models pixel motion, by predicting a distribution over pixel motion from previous frames. Because our model explicitly predicts motion, it is partially invariant to object appearance, enabling it to generalize to previously unseen objects. To explore video prediction for real-world interactive agents, we also introduce a dataset of 59,000 robot interactions involving pushing motions, including a test set with novel objects. In this dataset, accurate prediction of videos conditioned on the robot's future actions amounts to learning a "visual imagination" of different futures based on different courses of action. Our experiments show that our proposed method produces more accurate video predictions both quantitatively and qualitatively, when compared to prior methods.

We describe Swapout, a new stochastic training method, that outperforms ResNets of identical network structure yielding impressive results on CIFAR-10 and CIFAR-100. Swapout samples from a rich set of architectures including dropout, stochastic depth and residual architectures as special cases. When viewed as a regularization method swapout not only inhibits co-adaptation of units in a layer, similar to dropout, but also across network layers. We conjecture that swapout achieves strong regularization by implicitly tying the parameters across layers. When viewed as an ensemble training method, it samples a much richer set of architectures than existing methods such as dropout or stochastic depth. We propose a parameterization that reveals connections to exiting architectures and suggests a much richer set of architectures to be explored. We show that our formulation suggests an efficient training method and validate our conclusions on CIFAR-10 and CIFAR-100 matching state of the art accuracy. Remarkably, our 32 layer wider model performs similar to a 1001 layer ResNet model.

How long does it usually take you to pick out a new pair of glasses at the store? 10 minutes? When left unsupervised, I've admittedly taken over an hour. It's a big deal, as it is scientifically established that the type of glasses you wear impacts perception of your intelligence, success, and attractiveness. It's 2016; there must certainly be some sort of technology that has solved this problem. Of course there is! DITTO technologies developed a virtual mirror that allows customers to try on hundreds of products from the comfort of their homes.

Deep Learning compared to other Machine Learning methods is remarkably modular. This modularity gives it unprecedented capabilities that places Deep Learning head and shoulders above any other conventional Machine Learning approach. Recent research however is pointing to even greater modularity than previously. It is likely that quite soon, monolithic Deep Learning systems will become a thing of the past. Before I discuss what is coming in the future, let me first discuss the concept of modularity.

'Tis the season for the public relations exercise known as "here's what we think (or hope) will happen in the tech sector next year," flooding my inbox with predictions for 2017. No one knows what will happen tomorrow, let alone over the next 12 months, but the exercise yields interesting insights into what's hot (and what's not) in technology today. Artificial intelligence (and machine/deep learning) is the hottest trend, eclipsing, but building on, the accumulated hype for the previous "new big thing," big data. The new catalyst for the data explosion is the Internet of Things, bringing with it new cybersecurity vulnerabilities. The rapid fluctuations in the relative temperature of these trends also create new dislocations and opportunities in the tech job market.

Opinions expressed by Forbes Contributors are their own. The author is a Forbes contributor. The opinions expressed are those of the writer. We are witnessing a historic moment for technology advancement. Today we can pull together the best hardware, affordable infrastructure and vast amounts of data to fundamentally transform the way we conduct business.

These three books by highly respected academics / practitioners, and cover some of the most popular techniques in data mining and machine learning today. The previous section, Statistical Machine Learning, covers machine learning from the perspective of statisticians: creating statistical valid models of the data that can be used for predictions. This section, practical machine learning / data mining, deals more with the need to extract information and make predictions from large datasets. The first book, [ADVANCED] Mining of Massive Datasets [Check price on Amazon], is based off of Stanford's eponymous class, and covers popular problems such as recommendation systems, PageRank, and social network analysis. The second book, [ADVANCED] Deep Learning [Check price on Amazon], has draft chapters available for free.

What were the main advances in machine learning/artificial intelligence in 2016? Everyone now seems to be doing machine learning, and if they are not, they are thinking of buying a startup to claim they do. Now, to be fair, there are reasons for much of that "hype". Can you believe that it has been only a year since Google announced they were open sourcing Tensor Flow? TF is already a very active project that is being used for anything ranging from drug discovery to generating music.