In this blog, let us discuss what is Convolutional Neural Network (CNN) and the architecture behind Convolutional Neural Networks – which are designed to address image recognition systems and classification problems. Convolutional Neural Networks have wide applications in image and video recognition, recommendation systems and natural language processing. Consider this image of the New York skyline, upon first glance you will see a lot of buildings and colors. So how does the computer process this image? The image is broken down into 3 color-channels which is Red, Green and Blue.

For marketers, AI is perhaps the most intimidating abbreviation flying around the boardroom, the event hall, and the company Slack channel. But it doesn't have to be. Just as complex software deployments have become streamlined and marketer-friendly through software as a- service (SaaS), artificial intelligence will be going the same way much sooner than we all think. Before we talk AI, let's first talk personalization--a term marketers are far more comfortable with. Today, many brands face troubles when attempting effective personalization at scale.

The algorithms are well understood -- natural language processing, speech analytics, computer vision, and biometrics -- but we're only starting to come to grips with applications and with data, bias, and ethical implications. Emotion AI has many applications: consumer and market research, conversational interfaces, contact center operations, policy-making and finance, education, and, notably, healthcare uses that include suicide prevention. Potential but not-yet-fully-realized applications include emotionally intelligent design, design that aims to humanize technology. Actually, I wouldn't call the emotion AI potential of any application fully realized. That thought was the starting point for an exploratory conversation I had with Andy, who is professor of digital life at Bangor University in Wales and who'll be speaking at the up-coming Emotion AI Conference, taking place online on May 5th.

That information, known as the fundamental probabilities, was fed into Inspire Entertainment's computer models, which determined the final result by using those probabilities along with random number generation. The fundamental probabilities only determined the chances of each horse winning. Those with a higher probability value weren't necessarily going to win; they just had a greater chance of doing so.

The contribution of this paper is two-fold. First, we present ProbCast - a novel probabilistic model for multivariate time-series forecasting. We employ a conditional GAN framework to train our model with adversarial training. Second, we propose a framework that lets us transform a deterministic model into a probabilistic one with improved performance. The motivation of the framework is to either transform existing highly accurate point forecast models to their probabilistic counterparts or to train GANs stably by selecting the architecture of GAN's component carefully and efficiently. We conduct experiments over two publicly available datasets namely electricity consumption dataset and exchange-rate dataset. The results of the experiments demonstrate the remarkable performance of our model as well as the successful application of our proposed framework.

When it comes to finding a match/partner in the real world, it is usually an independent and autonomous task performed by people/entities. For a person, a match can be several things such as a romantic partner, business partner, school, roommate, etc. Our purpose in this paper is to train autonomous agents to find suitable matches for themselves using reinforcement learning. We consider the decentralized two-sided stable matching problem, where an agent is allowed to have at most one partner at a time from the opposite set. Each agent receives some utility for being in a match with a member of the opposite set. We formulate the problem spatially as a grid world environment and having autonomous agents acting independently makes our environment very uncertain and dynamic. We run experiments with various instances of both complete and incomplete weighted preference lists for agents. Agents learn their policies separately, using separate training modules. Our goal is to train agents to find partners such that the outcome is a stable matching if one exists and also a matching with set-equality, meaning the outcome is approximately equally likable by agents from both the sets.

Riemannian optimization has drawn a lot of attention due to its wide applications in practice. Riemannian stochastic first-order algorithms have been studied in the literature to solve large-scale machine learning problems over Riemannian manifolds. However, most of the existing Riemannian stochastic algorithms require the objective function to be differentiable, and they do not apply to the case where the objective function is nonsmooth. In this paper, we present two Riemannian stochastic proximal gradient methods for minimizing nonsmooth function over the Stiefel manifold. The two methods, named R-ProxSGD and R-ProxSPB, are generalizations of proximal SGD and proximal SpiderBoost in Euclidean setting to the Riemannian setting. Analysis on the incremental first-order oracle (IFO) complexity of the proposed algorithms is provided. Specifically, the R-ProxSPB algorithm finds an $\epsilon$-stationary point with $\mathcal{O}(\epsilon^{-3})$ IFOs in the online case, and $\mathcal{O}(n+\sqrt{n}\epsilon^{-3})$ IFOs in the finite-sum case with $n$ being the number of summands in the objective. Experimental results on online sparse PCA and robust low-rank matrix completion show that our proposed methods significantly outperform the existing methods that uses Riemannian subgradient information.

Recent advances in the theoretical understandingof SGD (Qian et al., 2019) led to a formula for the optimal mini-batch size minimizing the number of effective data passes, i.e., the number of iterations times the mini-batch size. However, this formula is of no practical value as it depends on the knowledge of the variance of the stochastic gradients evaluated at the optimum. In this paper we design a practical SGD method capable of learning the optimal mini-batch size adaptively throughout its iterations. Our method does this provably, and in our experiments with synthetic and real data robustly exhibits nearly optimal behaviour; that is, it works as if the optimal mini-batch size was known a-priori. Further, we generalize our method to several new mini-batch strategies not considered in the literature before, including a sampling suitable for distributed implementations.

Mutual Information (MI) plays an important role in representation learning. However, MI is unfortunately intractable in continuous and high-dimensional settings. Recent advances establish tractable and scalable MI estimators to discover useful representation. However, most of the existing methods are not capable of providing an accurate estimation of MI with low-variance when the MI is large. We argue that directly estimating the gradients of MI is more appealing for representation learning than estimating MI in itself. To this end, we propose the Mutual Information Gradient Estimator (MIGE) for representation learning based on the score estimation of implicit distributions. MIGE exhibits a tight and smooth gradient estimation of MI in the high-dimensional and large-MI settings. We expand the applications of MIGE in both unsupervised learning of deep representations based on InfoMax and the Information Bottleneck method. Experimental results have indicated significant performance improvement in learning useful representation.

We present a causal view on the robustness of neural networks against input manipulations, which applies not only to traditional classification tasks but also to general measurement data. Based on this view, we design a deep causal manipulation augmented model (deep CAMA) which explicitly models possible manipulations on certain causes leading to changes in the observed effect. We further develop data augmentation and test-time fine-tuning methods to improve deep CAMA's robustness. When compared with discriminative deep neural networks, our proposed model shows superior robustness against unseen manipulations. As a by-product, our model achieves disentangled representation which separates the representation of manipulations from those of other latent causes.