Neural networks provide the possibility to solve complicated non linear problems. They can be used in various areas such as signal classification, forecasting timeseries and pattern recognition. A neural network is a model inspired by the human brain and consists of multiple connected neurons. For getting a deeper understanding, I recommend checking out Neural Networks and Deep Learning. Within the last years, multiple Javascript frameworks were developed that can help you to create, train and use Neural Networks for different purposes.

We've been using TensorFlow in daily research and engineering since it was released almost six months ago. We've learned a lot of things along the way. Because there are many subjective articles on TensorFlow and not enough helpful documentation, I've sprinkled in examples, tutorials, docs, and code snippets wherever possible. When it comes to machine learning, it is easy to focus on the tech (features, capabilities, benchmarks, etc). But good programmers know it is much harder to write code that humans will use, versus code that a machine can compile and execute. So my favorite thing about TensorFlow is the simple fact that everyone in the machine learning community is aware of it, most are open to trying it, and hopefully, enough of us will use it to make useful things.

Nvidia's (NVDA) AI technology with Facebook (FB), Alphabet (GOOGL) and Microsoft (MSFT) is powering "superhuman" levels of inference, or artificial intelligence, Nvidia CEO Jen-Hsun Huang said Thursday, after the Tesla Motors (TSLA) partner blasted Q1 views on record deep-learning sales. "The truth is that nobody really knows how big this deep-learning market is going to be," Huang said on the company's earnings conference call. He referred specifically to gains that customer Microsoft was making with AI and deep learning. "The work that recently was done at Microsoft Research, they've achieved superhuman levels of inferencing … of image recognition and voice recognition that's really kind of hard to imagine," he said, "and these networks are now huge." In midday trading on the stock market today, Nvidia stock was up more than 14% and hit an all-time high at 40.30.

In a rare move, Apple has invested 1 billion in popular Chinese ride sharing service Didi Chuxing. The investment gives Apple an opportunity to learn more about its second-largest market, CEO Tim Cook said. "We are making the investment for a number of strategic reasons, including a chance to learn more about certain segments of the China market," Cook said in an interview with Reuters. "Of course, we believe it will deliver a strong return for our invested capital over time as well." The move also comes after billionaire investor Carl Icahn sold his position in Apple, largely due to the company's lagging performance in the region.

For the past few months, Google has been feeding erotic novels into a neural network with the hope of improving its conversation abilities and personality. Ignited, Fatal Desire and Jacked Up were just a few of the steamy romance novels on the AI's reading list. Now a selection of strange poems, or'homotopies', the AI has'written' after reading the novels has been published. The search giant's research team has witnessed the AI transcribe sentences that resembles those in the books, which will help the program inform and humanise the company's products. In a research paper, published on ArXiv and discovered by Quartz, the team describe some of the methods they have used to try and make the bot more conversational.

Dung beetles record a mental image of the positions of the Sun, the Moon and the stars and use the snapshot to navigate, according to researchers. Scientists in Sweden found that the beetles capture the picture of the sky while dancing on a ball of manure. As they roll away with their malodorous prize, the beetles compare the stored image with their current location. The beetles' navigational skills could aid the development of driverless vehicles, the researchers suggest. Previous studies have shown that dung beetles have an amazing ability to navigate by the light of the Milky Way.

Malaysia's strategic investment fund Khazanah Nasional Bhd is making a strategic investment of 100 million into New Jersey-based Fractal Analytics, a leading global provider of analytics, to accelerate its growth. In a press release, Khazanah executive director Chinta Bhagat commented: "The availability of large amounts of real-time information and the ability to analyse it at scale, will transform how the world makes decisions. Fractal is one of the companies leading this change and with our partnership, it can dramatically accelerate its programmatic investments and acquisitions." TA Associates, a Boston-based global private equity firm and AIMIA, the world's largest loyalty firm and Gulu Mirchandani of Onida are some of Fractal's current investors. Fractal Analytics co-founder and chief executive officer Srikanth Velamakanni said, the investment will allow the company to step up development of its artificial intelligence (AI) and deep learning-based software stack.

When you get right down to it, developing vaccines is about data and luck. Scientists start with a set of variables--what drugs a virus responds to, how effectively, and for whom--and then it's a whole lot of trial and error until they stumble upon a cure. One of the most exciting possibilities in medical research right now is how technology like machine learning could help researchers rapidly process those enormous sets of data, more quickly leading to cures. This is already starting to happen: In a study published Wednesday in the journal Macromolecules, researchers from IBM and Singapore's Institute of Bioengineering and Nanotechnology reveal a breakthrough that could help prevent deadly virus infections. With the help of IBM super computer Watson, they hope their finding will soon make its way into vaccines.

This post looks at perhaps the most important, and often overlooked, step in learning machine learning, an aspect which can make the biggest difference in one's skill set. The web is full of good explanations of machine learning algorithms. And every second applicant for a data science position has finished the Coursera course on machine learning. Theory will not help you choose good values for the 16 parameters a standard implementation of a random forest takes. The default values are good to get started, but which parameters should you modify depending on your data?

Researchers have developed a computer system that can train dogs without the help of a human. The team from North Carolina State University developed a harness which contains an array of sensors to monitor posture and body language. Using a small built-in computer to transmit data, the system can give out rewards for correct behaviour by releasing a treat from a nearby dispenser. The team from North Carolina State University developed a harness which contains an array of sensors to monitor posture and body language. Researchers from North Carolina State University developed a harness which contains an array of sensors to monitor posture and body language.