Recently, I rediscovered my passion for mathematics and artificial intelligence, which I used to hate while I was getting my degree in Computer Sciences. Lately, I've been focused on software design, automated testing, microservices, and functional programming. I also love learning new programming languages, so I've been wondering whether to go deeper into Golang, Scala, or Python. But in the end, all of them are tools -- tools for building what kind of things? In my case, my day-to-day job consists in building and maintaining microservices, as a full-stack developer.

These days, I am sure 90% of LinkedIn traffic contains one of these terms: DS, ML or DL -- acronyms for Data Science, Machine Learning or Deep Learning. Beware of the cliche though: "80% of all the statistics are made on the spot". If you blinked on these acronyms perhaps you need to google a bit and then continue reading the rest of this post. This post has 2 goals. First, it attempts to put all the fellow Data Science learners at ease.

They're often depicted as being lazy, but a new study suggests that teenagers are going through one of the best times to learn a new skill. Scientists have discovered increased activity in an area of the brain called the striatum in 17-20 year-olds, which boosts the way they learn from feedback. The findings suggest that adolescence is a unique life phase for increased feedback-learning performance. The researchers studied over 230 participants aged eight to 25. Each participant completed a feedback learning task, in which good performance was rewarded with positive feedback.

Microsoft took the wraps off a language learning app it described as "an always available, artificially intelligent" assistant. The app, Microsoft Learn Chinese, uses speech and natural language processing technology to enable learners to practice speaking the language. It uses "a suite of AI tools such as deep neural networks that have been tuned…to recognise what the language learners are trying to say and evaluate the speakers' pronunciation". Users get feedback in the form of scores, along with highlighted words which need improvement and links to sample audio to hear proper pronunciation. The machine-learning and neural networks powering the service are language-independent, Microsoft said. The app was developed in the computing giant's Asia research lab in Beijing.

Second-order methods for neural network optimization have several advantages over methods based on first-order gradient descent, including better scaling to large mini-batch sizes and fewer updates needed for convergence. But they are rarely applied to deep learning in practice because of high computational cost and the need for model-dependent algorithmic variations. We introduce a variant of the Hessian-free method that leverages a block-diagonal approximation of the generalized Gauss-Newton matrix. Our method computes the curvature approximation matrix only for pairs of parameters from the same layer or block of the neural network and performs conjugate gradient updates independently for each block. Experiments on deep autoencoders, deep convolutional networks, and multilayer LSTMs demonstrate better convergence and generalization compared to the original Hessian-free approach and the Adam method.

A regularized optimization problem over a large unstructured graph is studied, where the regularization term is tied to the graph geometry. Typical regularization examples include the total variation and the Laplacian regularizations over the graph. When applying the proximal gradient algorithm to solve this problem, there exist quite affordable methods to implement the proximity operator (backward step) in the special case where the graph is a simple path without loops. In this paper, an algorithm, referred to as "Snake", is proposed to solve such regularized problems over general graphs, by taking benefit of these fast methods. The algorithm consists in properly selecting random simple paths in the graph and performing the proximal gradient algorithm over these simple paths. This algorithm is an instance of a new general stochastic proximal gradient algorithm, whose convergence is proven. Applications to trend filtering and graph inpainting are provided among others. Numerical experiments are conducted over large graphs.

Check out the AI Business Summit at the AI Conference in New York, April 29 to May 2, 2018. Best price ends February 2. Artificial intelligence (AI) has attracted a lot of media coverage recently, and companies are rushing to figure out how AI technologies will impact them. Much of the coverage is devoted to research breakthroughs or new product offerings. But how are companies integrating AI into their underlying businesses? In this post, we share slides and notes from a talk we gave this past September at the AI Conference in San Francisco, offering an overview of the state of adoption and some suggestions to companies interested in implementing AI technologies.

Regularization in Machine Learning is an important concept and it solves the overfitting problem. It is very important to understand regularization to train a good model. Sometimes one resource is not enough to get you a good understanding of a concept. I have learnt regularization from different sources and I feel learning from different sources is very important. An easy and simple explanation is what everyone needs.

For the course "Deep Learning for Business," the first module is "Deep Learning Products & Services," which starts with the lecture "Future Industry Evolution & Artificial Intelligence" that explains past, current, and future industry evolutions and how DL (Deep Learning) and ML (Machine Learning) technology will be used in almost every aspect of future industry in the near future. The following lectures look into the hottest DL and ML products and services that are exciting the business world. Then the Amazon Echo and Echo Dot products are introduced along with the Alexa cloud based DL personal assistant that uses ASR (Automated Speech Recognition) and NLU (Natural Language Understanding) technology. The next lecture focuses on LettuceBot, which is a DL system that plants lettuce seeds with automatic fertilizer and herbicide nozzles control. Then the computer vision based DL blood cells analysis diagnostic system Athelas is introduced followed by the introduction of a classical and symphonic music composing DL system named AIVA (Artificial Intelligence Virtual Artist).

Human resources as a function has experienced significant changes in the last decade due to the evolution of technologies. Today, artificial intelligence (AI) is reshaping the way companies hire, manage and engage with their workforce. Advanced data-driven technology is rapidly making its way into the HR industry as businesses are focusing more on creating an employee-oriented corporate culture. Recruitment is no more a tedious process for HR practitioners as it no longer entails time-consuming activities such as manually screening the resumes of the prospective candidates, making phone calls or replying to candidates via emails. These mundane errands are now managed by smart technologies designed to replicate human conversation, thus enabling HR experts to contemplate the bigger picture.