The year is coming to an end. I did not write nearly as much as I had planned to. But I'm hoping to change that next year, with more tutorials around Reinforcement Learning, Evolution, and Bayesian Methods coming to WildML! And what better way to start than with a summary of all the amazing things that happened in 2017? Looking back through my Twitter history and the WildML newsletter, the following topics repeatedly came up.

Deep neural networks (DNNs) have enabled great progress in a variety of application areas, including image processing, text analysis, and speech recognition. DNNs are also being incorporated as an important component in many cyber-physical systems. For instance, the vision system of a self-driving car can take advantage of DNNs to better recognize pedestrians, vehicles, and road signs. However, recent research has shown that DNNs are vulnerable to adversarial examples: Adding carefully crafted adversarial perturbations to the inputs can mislead the target DNN into mislabeling them during run time. Such adversarial examples raise security and safety concerns when applying DNNs in the real world.

Recently, David Bader visited India to give a keynote talk at IEEE International Conference on Machine Learning and Data Science at Bennett University, Greater Noida. David A. Bader is Professor and Chair of the School of Computational Science and Engineering, College of Computing, at Georgia Institute of Technology. He is a fellow of the IEEE and AAAS and served on the White House's National Strategic Computing Initiative (NSCI) panel. He was in conversation with Prof. Deepak Garg, Chair, of Computer Science Engineering at Bennett University. Question: Big data and data analytics have made a huge impact on businesses in 2017, with trends like artificial intelligence and cloud services being used for their advantage.

Sometimes its ok and good for everyone to un-develop something existing to uncover the hidden gems which are already there and are useful. May be its like Un-Develop to Innovate? Alan Turing published "Turing Test" that speculates the possibility of creating machines that think. In order to pass the test, a computer must be able to carry on a conversation that was indistinctive from a conversation with a human being. This was the first serious proposal in the philosophy of artificial intelligence, which can be explained as: a science developing technology to mimic humans to respond in a circumstance.

When I first was introduced to the idea of adversarial learning for security purposes by Clarence Chio's 2016 DEF CON talk and his related open-source library deep-pwning, I immediately started wondering about applications of the field to both make robust and well-tested models, but also as a preventative measure against predatory machine learning practices in the field. After reading more literature and utilizing several other open-source libraries, I realized most examples and research focused around malicious uses, such as sending spam or malware without detection, or crashing self-driving cars. Although I find this research interesting, I wanted to determine if adversarial learning could be used for "good".1 In case you haven't been following the explosion of adversarial learning in neural network research, papers and conferences, let's take a whirlwind tour of some concepts to get on the same page and provide further reading if you open up arXiv for fun on the weekend. Similarly to how we use the loss function to train our network, researchers found we can use this same method to find weak links in our network and adversarial examples that exploit them.

Machine learning is different from traditional computation because it allows the computer to perform more advanced analysis of data, with or without the supervision of human operators. Supervised machine learning involves a human operator providing the computer with data, and then instructing the analytical software to look for specific information or answer more narrowly focused questions. Unsupervised machine learning is the most exciting. It involves giving a computer freedom to suck up data as needed, including real-time information. Then, it constantly runs analysis to find new patterns, discover new opportunities and report comprehensive information to decision-makers.

This is a follow up on my process of developing familiarity with computer vision and machine learning techniques. As a web developer (read as "rails developer"), I found this growing sphere exciting, but don't work with these technologies on a day-to-day. This is month three of a two year journey to explore this field. If you haven't read already, you can see Part 1 here: From webdev to computer vision and geo and Part 2 here: Two months exploring deep learning and computer vision. Rails developers are good at quickly building out web applications with very little effort.

One of the earliest goals for computers was the automatic translation of text from one language to another. Automatic or machine translation is perhaps one of the most challenging artificial intelligence tasks given the fluidity of human language. Classically, rule-based systems were used for this task, which were replaced in the 1990s with statistical methods. More recently, deep neural network models achieve state-of-the-art results in a field that is aptly named neural machine translation. In this post, you will discover the challenge of machine translation and the effectiveness of neural machine translation models.

We have an awesome deal on the Deep Learning and Artificial Intelligence Introductory Bundle in the Geeky Gadgets Deals store today, you can save 91% off the regular price. The Deep Learning and Artificial Intelligence Introductory Bundle is available in our deals store for just $39, it normally retails for $480. Deep Learning is a set of powerful algorithms that are the force behind self-driving cars, image searching, voice recognition, and many, many more applications we consider decidedly "futuristic." One of the central foundations of deep learning is linear regression; using probability theory to gain deeper insight into the "line of best fit." This is the first step to building machines that, in effect, act like neurons in a neural network as they learn while they're fed more information.

The picture is accurate, but the more relevant question is "When would each technique be at an advantage?" The obvious difference, correctly depicted, is that the Deep Neural Network is estimating many more parameters and even more permutations of parameters than the logistic regression. Therefore the real question is in what situations would that be a good idea? You need a good ratio of data points to parameters to get reliable estimates so the first criteria would be lots of data in order to estimate lots of parameters. If that's not true then you'd be estimating lots of parameters with little data per parameter and get a bunch of spurious results.