Large-scale datasets have played a significant role in progress of neural network and deep learning areas. YouTube-8M is such a benchmark dataset for general multi-label video classification. It was created from over 7 million YouTube videos (450,000 hours of video) and includes video labels from a vocabulary of 4716 classes (3.4 labels/video on average). It also comes with pre-extracted audio & visual features from every second of video (3.2 billion feature vectors in total). Google cloud recently released the datasets and organized 'Google Cloud & YouTube-8M Video Understanding Challenge' on Kaggle. Competitors are challenged to develop classification algorithms that assign video-level labels using the new and improved Youtube-8M V2 dataset. Inspired by the competition, we started exploration of audio understanding and classification using deep learning algorithms and ensemble methods. We built several baseline predictions according to the benchmark paper and public github tensorflow code. Furthermore, we improved global prediction accuracy (GAP) from base level 77% to 80.7% through approaches of ensemble.

Semantic boundary and edge detection aims at simultaneously detecting object edge pixels in images and assigning class labels to them. Systematic training of predictors for this task requires the labeling of edges in images which is a particularly tedious task. We propose a novel strategy for solving this task, when pixel-level annotations are not available, performing it in an almost zero-shot manner by relying on conventional whole image neural net classifiers that were trained using large bounding boxes. Our method performs the following two steps at test time. Firstly it predicts the class labels by applying the trained whole image network to the test images. Secondly, it computes pixel-wise scores from the obtained predictions by applying backprop gradients as well as recent visualization algorithms such as deconvolution and layer-wise relevance propagation. We show that high pixel-wise scores are indicative for the location of semantic boundaries, which suggests that the semantic boundary problem can be approached without using edge labels during the training phase.

Russia has retaliated by threatening to treat American planes as targets; in a dramatic "Top Gun"-style maneuver on Monday, one of Moscow's jets buzzed within five feet of an American spy plane. None of these encounters involved the Islamic State. The contradiction opens a larger question, national security experts say, of what kind of broader strategy the Trump administration plans once the Islamic State -- now on the defensive -- is defeated in Syria. With each episode, "we own more of the conflict in Syria without articulating a strategy," said Vali Nasr, dean of the Johns Hopkins School of Advanced International Studies. "We are sleepwalking into a much broader military mandate, without saying what we plan to do afterward."

Time is to speech and music recognition as space is to visual object recognition. We can think of recognizing a face in a drawing as a spatial problem--that is, the relevant information is contained in the spatial relationships between all the elements of the drawing. It is also a hierarchical problem: low-level information (lines and curves) must be integrated into a unified image. A circle is a circle, but two side-by-side pairs of concentric circles become eyes; place those in a larger circle and you have a face, and so forth until we have a crowd of people within a scene. Speech and music are the temporal equivalent of recognizing a visual scene: they require solving a hierarchy of embedded temporal problems.

Amazon started as an online bookseller 20 years ago. Since then, it has evolved into a technology juggernaut that has disrupted multiple markets and industries and touches many aspects of our lives. It is a relentless technology and business model innovator driving disruption throughout numerous ecosystems. Amazon's AWS revenues alone are approaching $16B a year making it one of the largest IT companies in the world. With dominant offerings in Cloud, IoT, eCommerce, Big Data, AI, Digital Assistants, Robotics, shipping logistics and other emerging technologies, developers and competitors ignore Amazon at their peril.

Everyone is talking about artificial intelligence (AI) right now- with many predicting that AI will lead the next wave of economic growth and productivity for the next couple of decades at least. However not all big-name AI stocks have the Street's seal of approval. Nvidia (NVDA) has a moderate buy analyst consensus rating while both Advanced Micro Devices (AMD) and Tesla (TSLA) have hold ratings. All three stocks have an average analyst price target below their current share price as analysts warn that prices have entered overblown territory (see Goldman Sachs' Toshiya Hari on AMD for example). To find less risky AI investing opportunities we looked for stocks with a strong buy consensus rating from the Street's best performing analysts.

It's good news for people who find work a drag, as Alibaba founder Jack Ma believes we will work just four hours a day for four days a week by 2047. The Chinese billionaire said he believed people would reap the benefits of artificial intelligence (AI) and be free to spend more time travelling and less time working. But the 52-year-old founder of Alibaba - China's equivalent of eBay - also warned'there's going to be trouble' with AI in the future unless governments move fast. The Chinese billionaire said he believed people would reap the benefits of artificial intelligence (AI) and be free to spend more time travelling and less time working. The 52-year-old Alibaba founder - China's equivalent of eBay - warned'there's going to be trouble' with AI in the future unless governments move fast.

Element AI, a Montreal-based studio that tackles problems using machine learning systems, announced a whopping $102 million in funding today. Data Collective led the round, which is one of the largest series A rounds for an AI company to date. The big check offers a massive war chest to Element, which connects businesses with machine learning experts who work to solve any problems they may have. Thanks to the new funds, Element AI will be able to expand its physical footprint. The company is opening offices in Toronto and Asia, according to Jean-François Gagné, the company's cofounder and CEO.

We talked a bit about the Software Development Life Cycle (SDLC) in a recent post, but today, we're going to dig a little deeper into one specific and crucial element in the testing phase, particularly for Agile development: regression testing. Definition of Regression Testing Regression testing refers to the process of testing a changed or updated computer program to make sure the older software features - which were previously developed and tested - still performs exactly as they did before. One way to think about software regression is to think about somebody who implements a new air conditioning system in their home only to find that while their new air conditioning system works as expected, the lights no longer work. Regression testing will often involve running existing tests against the modified code to make sure that the new code did not break anything that worked before the update. Regression testing can eliminate much of the risk associated with software updates.

Too often the answer to this question resembles the plot of a sci-fi thriller. People worry that developments in A.I. will bring about the "singularity" -- that point in history when A.I. surpasses human intelligence, leading to an unimaginable revolution in human affairs. Or they wonder whether instead of our controlling artificial intelligence, it will control us, turning us, in effect, into cyborgs. These are interesting issues to contemplate, but they are not pressing. They concern situations that may not arise for hundreds of years, if ever. At the moment, there is no known path from our best A.I. tools (like the Google computer program that recently beat the world's best player of the game of Go) to "general" A.I. -- self-aware computer programs that can engage in common-sense reasoning, attain knowledge in multiple domains, feel, express and understand emotions and so on.