Convolutional Neural Network (CNN) has become the most used method for image classification tasks. During its training the learning rate and the gradient are two key factors to tune for influencing the convergence speed of the model. Usual learning rate strategies are time-based i.e. monotonous decay over time. Recent state-of-the-art techniques focus on adaptive gradient algorithms i.e. Adam and its versions. In this paper we consider an online learning scenario and we propose two Event-Based control loops to adjust the learning rate of a classical algorithm E (Exponential)/PD (Proportional Derivative)-Control. The first Event-Based control loop will be implemented to prevent sudden drop of the learning rate when the model is approaching the optimum. The second Event-Based control loop will decide, based on the learning speed, when to switch to the next data batch. Experimental evaluationis provided using two state-of-the-art machine learning image datasets (CIFAR-10 and CIFAR-100). Results show the Event-Based E/PD is better than the original algorithm (higher final accuracy, lower final loss value), and the Double-Event-BasedE/PD can accelerate the training process, save up to 67% training time compared to state-of-the-art algorithms and even result in better performance.

Artificial Intelligence with TensorFlow is a four-week, part time, online training course that offers an introduction to neural networks, deep learning, machine learning, artificial intelligence and their many applications. This immersive, hands-on course teaches students the data science tools and techniques needed to build and test neural networks in TensorFlow using real-world data. This course is optimal for those who have taken Essential Data Tools & Practical Machine Learning and desire to expand their knowledge of modeling and data science with TensorFlow.

When VentureBeat asked Andrew Burt why he was starting an AI-focused law firm, Burt was quick to clarify that it's about AI and analytics. But that didn't answer the underlying question of why the world needs a law firm focused so precisely on this one key area. "The thesis behind the law firm is that traditional legal expertise on its own is not sufficient," said Burt, a Yale Law School alum. His partner is data scientist Patrick Hall, and together they aim to provide legal acumen around AI and analytics that's bolstered by technical understanding. "If we are going to successfully manage the risks of AI and advanced analytics, we need both of these types of expertise commingled," added Burt. Called bnh.ai (techy shorthand for "Burt and Hall"), the firm is located in Washington, D.C., which Burt says confers a key advantage.

A basic grounding in the principles and practices around artificial intelligence (AI), automation and cognitive systems is something which is likely to become increasingly valuable, regardless of your field of business, expertise or profession. Fortunately, today you don't have to take years out of your life studying at university to become familiar with this seemingly hugely complex technology. A growing number of online courses have sprung up in recent years covering everything from the basics to advanced implementation. Some are aimed at people who want to dive straight into coding their own artificial neural networks, and understandably assume a certain level of technical ability. Others are useful for those who want to learn how this technology can be applied by anyone, regardless of prior technical expertise, to solving real-word problems.

We propose a novel method for {\em linear} dimensionality reduction of manifold modeled data. First, we show that with a small number $M$ of {\em random projections} of sample points in $\reals N$ belonging to an unknown $K$-dimensional Euclidean manifold, the intrinsic dimension (ID) of the sample set can be estimated to high accuracy. Second, we rigorously prove that using only this set of random projections, we can estimate the structure of the underlying manifold. In both cases, the number random projections required is linear in $K$ and logarithmic in $N$, meaning that $K M\ll N$. To handle practical situations, we develop a greedy algorithm to estimate the smallest size of the projection space required to perform manifold learning.

We show a principled way of deriving online learning algorithms from a minimax analysis. Various upper bounds on the minimax value, previously thought to be non-constructive, are shown to yield algorithms. This allows us to seamlessly recover known methods and to derive new ones, also capturing such ''unorthodox'' methods as Follow the Perturbed Leader and the R 2 forecaster. Understanding the inherent complexity of the learning problem thus leads to the development of algorithms. To illustrate our approach, we present several new algorithms, including a family of randomized methods that use the idea of a ''random play out''.

Artificial Intelligence (AI) has the potential to transform learning for K-12 students nationwide. Rather than receiving the same instruction and content as classmates with differing interests, ability levels, and capabilities, students can experience learning that is truly personalized and work at their own pace with needed instructional supports, engaging content in areas that pique their curiosity, automated scoring and instant feedback, messages of encouragement, and opportunities to take a break provided for them at just the right time. As the leading provider of virtual education for K-12 students, our company--K12--is executing on a multi-year roadmap to deliver this type of experience for our students. The first, and I believe most important, role that AI can serve is to match students to instruction at their individual learner level, focused on the right skills, delivered in the right progression, and in the mode of instruction--video, interactive examples, guided practice, etc.--that is most effective for each student. Students learn differently, have distinct strengths and weaknesses, and progress at their own pace.

The Lovasz $\theta$ function of a graph, is a fundamental tool in combinatorial optimization and approximation algorithms. Computing $\theta$ involves solving a SDP and is extremely expensive even for moderately sized graphs. In this paper we establish that the Lovasz $\theta$ function is equivalent to a kernel learning problem related to one class SVM. This interesting connection opens up many opportunities bridging graph theoretic algorithms and machine learning. We show that there exist graphs, which we call $SVM-\theta$ graphs, on which the Lovasz $\theta$ function can be approximated well by a one-class SVM.

The global artificial intelligence and education Market is significantly driven by the integration of intelligent algorithms as well as Advanced Technologies in to e-learning platforms. Education software, machine learning, and artificial intelligence are some of the Innovative learning models and Technologies change the rules and creating tremendous shift from the teaching methods. These technologies have completely transformed with a classroom. The sophistication level has increased tremendously with the increasing adoption of artificial intelligence and machine learning algorithms. These Technologies are becoming extremely useful for developing user-friendly decision support systems and used in knowledge acquisition applications, language translation, and information retrieval.

For a child prodigy, learning didn't always come easily to Derek Haoyang Li. When he was three, his father – a famous educator and author – became so frustrated with his progress in Chinese that he vowed never to teach him again. "He kicked me from here to here," Li told me, moving his arms wide. Yet when Li began school, aged five, things began to click. Five years later, he was selected as one of only 10 students in his home province of Henan to learn to code. At 16, Li beat 15 million kids to first prize in the Chinese Mathematical Olympiad. Among the offers that came in from the country's elite institutions, he decided on an experimental fast-track degree at Jiao Tong University in Shanghai. It would enable him to study maths, while also covering computer science, physics and psychology. In his first year at university, Li was extremely shy.