--Automated machine learning has gained a lot of attention recently. Building and selecting the right machine learning models is often a multi-objective optimization problem. General purpose machine learning software that simultaneously supports multiple objectives and constraints is scant, though the potential benefits are great. In this work, we present a framework called Autotune that effectively handles multiple objectives and constraints that arise in machine learning problems. Autotune is built on a suite of derivative-free optimization methods, and utilizes multilevel parallelism in a distributed computing environment for automatically training, scoring, and selecting good models. Incorporation of multiple objectives and constraints in the model exploration and selection process provides the flexibility needed to satisfy tradeoffs necessary in practical machine learning applications. Experimental results from standard multi-objective optimization benchmark problems show that Autotune is very efficient in capturing Pareto fronts. These benchmark results also show how adding constraints can guide the search to more promising regions of the solution space, ultimately producing more desirable Pareto fronts. Results from two real-world case studies demonstrate the effectiveness of the constrained multi-objective optimization capability offered by Autotune. There has been increasing interest in automated machine learning (AutoML) for improving data scientists' productivity and reducing the cost of model building. A number of general or specialized AutoML systems have been developed [1]- [7], showing impressive results in creating good models with much less manual effort. Most of these systems only support a single objective, typically accuracy or error, to assess and compare models during the automation process.

State-of-the-art machine learning frameworks support a wide variety of design features to enable a flexible machine learning programming interface and to ease the programmability burden on machine learning developers. Identifying and using a performance-optimal setting in feature-rich frameworks, however, involves a non-trivial amount of performance characterization and domain-specific knowledge. This paper takes a deep dive into analyzing the performance impact of key design features and the role of parallelism. The observations and insights distill into a simple set of guidelines that one can use to achieve much higher training and inference speedup. The evaluation results show that our proposed performance tuning guidelines outperform both the Intel and TensorFlow recommended settings by 1.29x and 1.34x, respectively, across a diverse set of real-world deep learning models.

Artificial Intelligence, or AI for short, has become quite the public buzzword. Companies and investors are pouring money into the field. Universities -- even high schools -- are rushing to start new degree programs or colleges dedicated to AI. Civil society organizations are scrambling to understand the impact of AI technology on humanity, and governments are competing to encourage or regulate AI research and deployment. One country, the United Arab Emirates, even boasts a minister for AI. At the same time, the world's militaries are developing AI-based weaponry to defeat their enemies, police agencies are experimenting with AI as a surveillance tool to identify or interrogate suspects, and companies are testing its ability to replace humans in menial or more meaningful jobs -- all of which may change the equation of life for all of the world's people.

This video is part of an online course, End-to-End Machine Learning with Tensorflow from Google Cloud. About this course: In the first course of this specialization, we will recap what was covered in the Machine Learning with TensorFlow on Google Cloud Platform Specialization. One of the best ways to review something is to work with the concepts and technologies that you have learned.

Have anything in mind that you think is awesome and would fit in this list? Feel free to send a pull request.

Last week, I reviewed Thomas Siebel's surprisingly good Digital Transformation: Survive and Thrive in an Era of Mass Extinction. The components that makeup Siebel's digital transformation are: cloud computing, big data, IoT (internet of things), and AI (artificial intelligence). In that review, I asked if any books examine the impact of these technologies on the future of higher ed? But maybe that is the wrong question. A better approach might be to ask: what are the academic analogs of each of the components of digital transformation?

Today's operators are undergoing vast digital transformations to help shape their roadmaps for future innovation. That includes transforming existing networks to more virtualised environments and preparing for 5G. The new networks must be more robust and agile and at the same time, able to adapt to whatever the future will bring, Anand Gonuguntla, co-founder and CEO of Centina. Operators must also be prepared to manage a continued trend of software as a service and cloud-based service models. Assuring quality of existing and future services becomes both more challenging and more critical to these operators as the competition heats up.

Cross-lingual representations of words enable us to reason about word meaning in multilingual contexts and are a key facilitator of cross-lingual transfer when developing natural language processing models for low-resource languages. In this survey, we provide a comprehensive typology of cross-lingual word embedding models. We compare their data requirements and objective functions. The recurring theme of the survey is that many of the models presented in the literature optimize for the same objectives, and that seemingly different models are often equivalent, modulo optimization strategies, hyper-parameters, and such. We also discuss the different ways cross-lingual word embeddings are evaluated, as well as future challenges and research horizons.

Deep Reinforcement Learning has made significant progress in multi-agent systems in recent years. In this review article, we have mostly focused on recent papers on Multi-Agent Reinforcement Learning (MARL) than the older papers, unless it was necessary. Several ideas and papers are proposed with different notations, and we tried our best to unify them with a single notation and categorize them by their relevance. In particular, we have focused on five common approaches on modeling and solving multi-agent reinforcement learning problems: (I) independent-learners, (II) fully observable critic, (III) value function decomposition, (IV) consensus, (IV) learn to communicate. Moreover, we discuss some new emerging research areas in MARL along with the relevant recent papers. In addition, some of the recent applications of MARL in real world are discussed. Finally, a list of available environments for MARL research are provided and the paper is concluded with proposals on the possible research directions.

Acquiring new robot motor skills is cumbersome, as learning a skill from scratch and without prior knowledge requires the exploration of a large space of motor configurations. Accordingly, for learning a new task, time could be saved by restricting the parameter search space by initializing it with the solution of a similar task. We present a framework which is able of such knowledge transfer from already learned movement skills to a new learning task. The framework combines probabilistic movement primitives with descriptions of their effects for skill representation. New skills are first initialized with parameters inferred from related movement primitives and thereafter adapted to the new task through relative entropy policy search. We compare two different transfer approaches to initialize the search space distribution with data of known skills with a similar effect. We show the different benefits of the two knowledge transfer approaches on an object pushing task for a simulated 3-DOF robot. We can show that the quality of the learned skills improves and the required iterations to learn a new task can be reduced by more than 60% when past experiences are utilized.