Last year Hrayr used convolutional networks to identify spoken language from short audio recordings for a TopCoder contest and got 95% accuracy. After the end of the contest we decided to try recurrent neural networks and their combinations with CNNs on the same task. The best combination allowed to reach 99.24% and an ensemble of 33 models reached 99.67%. As before, the inputs of the networks are spectrograms of speech recordings. It seems spectrograms are the standard way to represent audio for deep learning systems (see "Listen, Attend and Spell" and "Deep Speech 2: End-to-End Speech Recognition in English and Mandarin").

Twitter (NYSE:TWTR) recently acquired Magic Pony technologies, a machine learning startup focusing on deep learning in computer vision. In my continuing coverage of the AI market, I want to briefly comment on this transaction. First, another contributor has already commented and described the company's product (without technical details). At its core, Magic Pony uses machine learning to enhance low resolution images and videos. It is quite remarkable when you think about it.

Due to the recent achievements of artificial neural networks across many different tasks (such as face recognition, object detection and Go), deep learning has become extremely popular. This post aims to be a starting point for those interested in learning more about it. If you already have a basic understanding of linear algebra, calculus, probability and programming: I recommend starting with Stanford's CS231n. The course notes are comprehensive and written well. The slides for each lesson are also available, and even though the accompanying videos were removed from the official site, re-uploads are quite easy to find online.

It uses artificial intelligence (AI) to automatically convert data into semantic knowledge. Diffbot uses deep-learning technology to categorize webpage data according to its meaning. Essentially, it provides users with structured knowledge sorted in human-like categories. The web-scrapping company can suck up content from homepages, articles, products, and social network profiles, which can aid both, app developers as well as enterprises, to do competitive analysis and gain insights into consumers. With the use of AI, Diffbot has already surpassed the data bank of Google's Knowledge Graph.

This structural design can support calculations being made upon thousands of layers, and it was this aspect of the architecture that gave rise to the name'deep learning'. Marchand-Maillet explains: "Each artificial neurone is assigned an input value, which it computes using a mathematical function, only firing if the output exceeds a pre-defined threshold." In this way, it reproduces the behaviour of real neurones, which only fire and transmit information when the input signal (the potential difference across the entire neural circuit) reaches a certain level. In the artificial model, the results of a single layer are weighted, added up and then sent as the input signal to the following layer, which processes that input using different functions, and so on and so forth. For example, if a system is trained with great quantities of photos of apples and watermelons, it will progressively learn to distinguish them on the basis of diameter, says Marchand-Maillet. If it cannot decide (e.g., when processing a picture of a tiny watermelon), the subsequent layers take over by analysing the colours or textures of the fruit in the photo, and so on.

CVPR 2016 -- CEVA, Inc. (NASDAQ: CEVA), the leading licensor of signal processing IP for smarter, connected devices, today introduced CDNN2 (CEVA Deep Neural Network), its second generation neural network software framework for machine learning. CDNN2 enables localized, deep learning-based video analytics on camera devices in real time. This significantly reduces data bandwidth and storage compared to running such analytics in the cloud, while lowering latency and increasing privacy. Coupled with the CEVA-XM4 intelligent vision processor, CDNN2 offers significant time-to-market and power advantages for implementing machine learning in embedded systems for smartphones, advanced driver assistance systems (ADAS), surveillance equipment, drones, robots and other camera-enabled smart devices. CDNN2 builds on the successful foundations of CEVA's first generation neural network software framework (CDNN), which is already in design with multiple customers and partners.

Deep learning is the new big trend in machine learning. It had many recent successes in computer vision, automatic speech recognition and natural language processing. The goal of this blog post is to give you a hands-on introduction to deep learning. To do this, we will build a Cat/Dog image classifier using a deep learning algorithm called convolutional neural network (CNN) and a Kaggle dataset. This post is divided into 2 main parts. The first part covers some core concepts behind deep learning, while the second part is structured in a hands-on tutorial format. In the first part of the hands-on tutorial (section 4), we will build a Cat/Dog image classifier using a convolutional neural network from scratch.

In a match last October, the AlphaGo program developed by Google's "DeepMind" subsidiary beat, 5 games to 0, the French professional player Fan Hui,1 who is ranked 2 dan (on the professional scale from 1 dan to 9 dan) and is today Europe's best player. The story was related by the journal Nature.2 This was the first time that a computer beats a professional player. But in the world of artificial intelligence, the progress demonstrated by the AlphaGo victory wasn't expected for another ten years or so. The moment of truth, however, will take place between March 9-15 in Seoul, where AlphaGo will face the South Korean Lee Se-dol, who is 9 dan, and is considered the best player in the world as well as a Go living legend. This new game, which will be broadcast live on the Web, comes with a 1,000,000 prize for the human champion if he wins.

It's all about trying to teach computers to make connections, similar to those humans make instinctively when growing up, in distinguishing objects. When it comes to video content, machine learning can help solve one of the growing issues in the industry. Barry Schwarz calls it'the paradox of choice' which he describes in his book and his excellent TED talk. Simply put, there has been an explosion of high quality video content production over the last decade. In 2014, Annalect reported that US consumers wanting to watch episodic TV had over 350 to choose from. Yet, consumers are less happy now than when they had fewer choices. It turns out that too many choices just make decisions harder. So, as an industry, we must come up with new ways of getting a better understanding of what each consumer wants to watch and create tools that will make discovery and recommendation more seamless and effective. In fact, machine learning could very well be the driver of a completely new set of content discovery and hyper-personalized services that will dramatically improve viewer satisfaction.

AlphaGo, the board-game-playing AI from Google's DeepMind subsidiary, is one of the most famous examples of deep learning – machine learning using neural networks – to date. So it may be surprising to learn that some of the code that led to the machine's victory was created by good old-fashioned humans. The software, which beat Korean Go Champion Lee Sedol 4–1 in March, taught itself to play the ancient Asian game by running millions of simulations against itself. AlphaGo is one of two neural networks, taught by a mixture of supervised learning (studying previous games played by humans) and reinforcement learning (playing against itself and learning from its mistakes). But some things, it turns out, just can't be taught.