Visual Question Answering (VQA) is an increasingly popular topic in deep learning research, requiring coordination of natural language processing and computer vision modules into a single architecture. We build upon the model which placed first in the VQA Challenge by developing thirteen new attention mechanisms and introducing a simplified classifier. We performed 300 GPU hours of extensive hyperparameter and architecture searches and were able to achieve an evaluation score of 64.78%, outperforming the existing state-of-the-art single model's validation score of 63.15%.

Want to watch this again later? Sign in to add this video to a playlist. Report Need to report the video? Sign in to report inappropriate content. Report Need to report the video?

Want to watch this again later? Sign in to add this video to a playlist. Report Need to report the video? Sign in to report inappropriate content. Report Need to report the video?

The feature appears to work by asking the app to play an artist, album, song, genre or playlist. Hunter found it by pulling up Spotify's search screen. In the bottom right-hand corner, there was a microphone button. Hitting it brought up entirely new voice options. This venture makes sense, given Spotify's hardware ambitions.

Historically, building a system that can answer natural language questions about any image has been considered a very ambitious goal. So, how many players are in the image? Well, we can count them and see that there are eleven players, since we are smart enough not to count the referee, right? Although as humans we can normally perform this task without major inconveniences, the development of a system with these capabilities has always seemed closer to science fiction than to the current possibilities of Artificial Intelligence (AI). However, with the advent of Deep Learning (DL), we have witnessed enormous research progress in Visual Question Answering (VQA), in such a way that systems capable of answering these questions are emerging with promising results. In this article I will briefly go through some of the current datasets, approaches and evaluation metrics in VQA, and on how this challenging task can be applied to real life use cases.

Orange Bank has entered the banking market with Djingo, a virtual advisor powered by IBM's Watson. "The virtual advisor brings customers a unique experience allowing them to interact with their bank when and where they want," said André Coisne, CEO of Orange Bank. For the French, mobile banking is becoming the preferred mode of interaction with their bank. Today, nearly two out of three (63%) French people have downloaded their bank's app on their mobile, and almost half (47%) consult their app at least once a week*. Orange Bank offers a new quality of customer services through a virtual advisor called'Djingo', which is powered by IBM Watson delivered through IBM Services.

In 2015, 1.7 million voice-first devices were shipped across the U.S. But the number soon rose up to 6.5 million in 2016. The increase in the trend captured the growing demand for voice-search in the coming years. Voice-search technology has existed for many years but its evolution has just begun. From automated voice recognition phone system to simplified voice to text dictaphones, voice technology was adopted in different forms all across the globe.

The role of artificial intelligence in advertising is leaping from the experimental stage to something more commonplace, as all marketers want to reach "the right person, at the right time, at the right place with the right message." That was the impetus behind lawn care services chain TruGreen's expanded use of IBM Watson Advertising's AI tools to target specific customers with ads recommending specific offers related to local conditions. TruGreen boasts 2.3 million commercial and residential customers with 260 lawn care branches in the United States and Canada, plus about 35 franchise locations. To reach those people and businesses with a timely message about their individual lawn care needs, the IBM Watson ads takes in many factors that might come into play, such as weeds, thin grass, dryness, lack of growth, or grass discoloration. "At TruGreen, we are constantly looking for new and innovative ways to interact with consumers," said Kari Rajaniemi, Chief Marketing Officer, TruGreen.

"Orange Bank has entered the banking market with an innovative, new offer. Djingo powered by Watson is one of the bank's innovations. The virtual advisor brings our customers a unique experience allowing them to interact with their bank when and where they want," said André Coisne, CEO of Orange Bank. For the French, mobile banking is becoming the preferred mode of interaction with their bank. Today, nearly two out of three (63%) French people have downloaded their bank's app on their mobile, and almost half (47%) consult their app at least once a week*.

IBM Watson CTO Rob High has done a lot of thinking about the privacy, security, and ethical implications of artificial intelligence. He presented some of those ideas at Mobile World Congress 2018, and we talked to him about some of his key findings. You can watch the interview above or read the transcript below. High said, "One of the things we have to realize about AI--it's relatively new to all of us. There's a lot about it that we don't all fully understand. Even as a technologist, we know where we're trying to bring the technology, but on the other side there's lots of people for which this technology is new. The experiences around that are going to be different. As with any new technology, it's really important that we be thinking now about how we do that ethically and responsibly. For us, that comes down to three basic principles. "What that basically means is that when you're using an AI technology, you have to trust that it's going to be doing the right thing.