Ever wanted to develop your own artificially-intelligent programs? Microsoft is empowering everyone with the capability to create huge, intelligent data-processing systems with the release of the Cognitive Toolkit. The Cognitive Toolkit--previously known as CNTK--is a superfast deep-learning toolkit that brings commercial-grade quality and processing accuracy together with programming languages and algorithms you already use. It's not just for developers with a farm of servers and GPUs, though--hobbyists and modest users can be equally competitive because the Toolkit is flexible enough to run on a single laptop. Developers can also integrate into the Toolkit their own Python or C code.

Sequence-to-Sequence (seq2seq) modeling has rapidly become an important general-purpose NLP tool that has proven effective for many text-generation and sequence-labeling tasks. Seq2seq builds on deep neural language modeling and inherits its remarkable accuracy in estimating local, next-word distributions. In this work, we introduce a model and beam-search training scheme, based on the work of Daume III and Marcu (2005), that extends seq2seq to learn global sequence scores. This structured approach avoids classical biases associated with local training and unifies the training loss with the test-time usage, while preserving the proven model architecture of seq2seq and its efficient training approach. We show that our system outperforms a highly-optimized attention-based seq2seq system and other baselines on three different sequence to sequence tasks: word ordering, parsing, and machine translation.

Thanks! We'll email you when relevant content is added and updated. We'll email you when relevant content is added and updated. We'll email you when relevant content is added and updated. We'll email you when relevant content is added and updated. If you answer the question with another -- Does it matter?

This is my multi-month study plan for going from mobile developer (self-taught, no CS degree) to machine learning engineer. My main goal was to find an approach to studying Machine Learning that is mainly hands-on and abstracts most of the math for the beginner. This approach is unconventional because it's the top-down and results-first approach designed for software engineers. Please, feel free to make any contributions you feel will make it better. I'm following this plan to prepare for my near future job: Machine learning engineer.

Guardian Analytics has released the Guardian Analytics Sentinel, a behavioral analytics and machine learning solution to protect B2B portals. This solution can be used to detect a wide array of fraud types including: account takeover, business email compromise (BEC), fake invoicing, fake purchase orders and modified wire and ACH templates. Built on an open API, Guardian Analytics Sentinel provides a real-time risk-scoring engine that does not require manual intervention. The machine-to-machine architecture allows for deployment as fast as 60 days. Guardian Analytics is a US-based company providing behavior-based fraud detection software and services to identify suspicious financial activities.

Machine learning may once have been a topic of discussion only for computer scientists and researchers. Now, however, it is a technology businesses are eager to use. The need for machine learning and Artificial Intelligence (AI) is being driven by the massive amount of data being generated today. Statisticians can get insight from this data. But the volume is so large and growing at such a rate, the best way to tackle it is using the very same machines that are in part responsible for creating the data.

Automated machine learning has become a topic of considerable interest over the past several months. A recent KDnuggets blog competition focused on this topic, and generated a handful of interesting ideas and projects. Of note, our readers were introduced to Auto-sklearn, an automated machine learning pipeline generator, via the competition, and learned more about the project in a follow-up interview with its developers. Prior to that competition, however, KDnuggets readers were introduced to TPOT, "your data science assistant," an open source Python tool that intelligently automates the entire machine learning process. For scikit-learn-compatible datasets, TPOT can automatically optimize a series of feature preprocessors and machine learning models that maximize the dataset's cross-validation accuracy, and outputs the optimal model as Python code leveraging scikit-learn.

A major challenge in crowdsourcing evaluation tasks like labeling objects, grading assignments in online courses, etc., is that of eliciting truthful responses from agents in the absence of verifiability. In this paper, we propose new reward mechanisms for such settings that, unlike many previously studied mechanisms, impose minimal assumptions on the structure and knowledge of the underlying generating model, can account for heterogeneity in the agents' abilities, require no extraneous elicitation from them, and furthermore allow their beliefs to be (almost) arbitrary. These mechanisms have the simple and intuitive structure of an output agreement mechanism: an agent gets a reward if her evaluation matches that of her peer, but unlike the classic output agreement mechanism, this reward is not the same across evaluations, but is inversely proportional to an appropriately defined popularity index of each evaluation. The popularity indices are computed by leveraging the existence of a large number of similar tasks, which is a typical characteristic of these settings. Experiments performed on MTurk workers demonstrate higher efficacy (with a $p$-value of $0.02$) of these mechanisms in inducing truthful behavior compared to the state of the art.

Machine Learning is one of the most exciting fields in the world. Every week we discover something new, something amazing, something revolutionary. It's incredible, but it can also be overwhelming. That's why we created This Week in Machine Learning! Each week we publish a curated list of Machine Learning stories as a resource to help you keep pace with all these exciting developments.

"Every aspect of our lives will be transformed. In short, success in creating AI could be the biggest event in the history of our civilization." From self-driving vehicles to virtual assistants, artificial intelligence (AI) is evolving at a rapid pace. It has the potential for tremendous good – IBM's Watson improving cancer treatment with genomic sequencing as an example. Additionally, AI has been used to bring new art into the world – "Symphonologie" is an orchestra piece created with the help of AI.