UAlberta expertise brings DeepMind lab to Edmonton

Expertise in artificial intelligence brings Alphabet's @DeepMindAI lab to #yeg.

  • The DeepMind Alberta team will be led by UAlberta computing science professors Richard Sutton, Michael Bowling, and Patrick Pilarski.
  • So when we chose to set up our first international AI research office, the obvious choice was his base in Edmonton, in close collaboration with the University of Alberta, which has become a leader in reinforcement learning research thanks to his pioneering work,” said Demis Hassabis, CEO and co-founder of DeepMind. ”
  • Sutton is excited about the opportunity to combine the strength of DeepMind’s work in reinforcement learning with UAlberta’s academic excellence, all without having to leave Edmonton.
  • “DeepMind has taken this reinforcement learning approach right from the very beginning, and the University of Alberta is the world’s academic leader in reinforcement learning, so it’s very natural that we should work together,” said Sutton.
  • Working with Hassabis and the DeepMind team both in London and Edmonton, Sutton, Bowling, and Pilarski will combine their academic strength in reinforcement learning to focus on basic AI research.

University of Alberta
Continue reading “UAlberta expertise brings DeepMind lab to Edmonton”

Taxonomy of Methods for Deep Meta Learning

Taxonomy of Methods for Deep Meta Learning #NeuralNetworks #DeepLearning

  • A recent paper, “Evolving Deep Neural Networks” provides a comprehensive list of global parameters that are typically used in the conventional search approaches (i.e. Learning rate) as well as more hyperparameters that involve more details about the architecture of the Deep Learning network.
  • Two recent papers that were submitted to ICLR 2017 explore the use of Reinforcement learning to learn new kinds of Deep Learning architectures (“Designing Neural Network Architectures using Reinforcement Learning” and “Neural Architecture Search with Reinforcement Learning”).
  • The first paper describes the use of Reinforcement Q-Learning to discover CNN architectures, you can find some of their generated CNNs in Caffe These are the different parameters that are sampled by the MetaQNN algorithm:

    The second paper (Neural Architecture Search) employs uses Reinforcement Learning (RL) to train a an architecture generator LSTM to build a language that describes new DL architectures.

  • In all the above approaches, the method employs different search mechanisms (i.e. Grid, Gaussian Processes, Evolution, Q-Learning, Policy Gradients) to discover (among the many generated architectures) better configurations.
  • We have a glimpse of a DSL driven architecture in my previous post about “A Language Driven Approach to Deep Learning Training” where a prescription that is quite general is presented.


This post discusses a variety of contemporary Deep Meta Learning methods, in which meta-data is manipulated to generate simulated architectures. Current meta-learning capabilities involve either support for search for architectures or networks inside networks.

Continue reading “Taxonomy of Methods for Deep Meta Learning”

Salesforce created an algorithm that automatically summarizes text using machine learning

Salesforce created an algorithm that automatically summarizes text using machine learning

  • To help solve this problem, researchers at Salesforce have developed an algorithm that uses machine learning to produce “surprisingly coherent and accurate” summaries according to MIT Technology Review.
  • To that end, Salesforce is turning to machine learning to find ways to summarize longer blocks of texts, which it could eventually incorporate into its products.
  • Together, the two advances allow researchers to automatically create summaries of longer texts that are accurate and readable.
  • Salesforce’s approach uses two teaching methods: teacher forced and reinforcement learning
    The other breakthrough concerns how the researchers train the system to learn and improve itself.
  • The results are pretty astonishing: the researchers provided several examples, showing the original article, a human-generated summary, and a summary generated by their own model, and in each case, the summaries are considerably shorter than the original text, but contain the essentials in a readable form.

This year, people are expected to spend more than half their day reading e-mail, articles, or posts on social media, and it’s only going to get worse. To help solve this problem, researchers at…
Continue reading “Salesforce created an algorithm that automatically summarizes text using machine learning”

Why nature is our best guide for understanding artificial intelligence

Why nature is our best guide for understanding artificial intelligence  #ai #machinelearning

  • Google’s AI translation tool seems to have invented its own secret internal language
  • There’s great opportunity in AI, and natural evolution provides a framework for us to study and prepare for the future of machine evolution.
  • For the sake of our comparison (natural evolution to machine evolution), let’s consider data and how it is normalized as “the environment” and the training process as “Natural Selection.
  • Big data company Palantir quietly raised another $20M in November
  • Much like natural evolution, different organisms solve for the same problem differently depending on their environment, but ultimately reach the same outcome.

In living organisms, evolution is a multi-generational process where mutations in genes are dropped and added. Well-adapted organisms survive and those less..
Continue reading “Why nature is our best guide for understanding artificial intelligence”

5 EBooks to Read Before Getting into A Machine Learning Career

#ICYMI 5 #MachineLearning EBooks

  • The Deep Learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general and deep learning in particular.
  • A carefully-curated list of 5 free ebooks to help you better understand the various aspects of what machine learning, and skills necessary for a career in the field.
  • The online version of the book is now complete and will remain available online for free.
  • Sure, many important advancements have been made in machine learning since this was put together, as Nilsson himself says, but these notes cover much of what is still considered relevant elementary material in a straightforward and focused manner.
  • Well, there’s always a collection of tutorials on pursuing machine learning in the Python ecosystem.


A carefully-curated list of 5 free ebooks to help you better understand the various aspects of what machine learning, and skills necessary for a career in the field.

Continue reading “5 EBooks to Read Before Getting into A Machine Learning Career”

Advancing our ambition to democratize artificial intelligence

Microsoft + OpenAI partner to bring AI to everyone

  • The week at Microsoft Ignite, we showed how we are infusing artificial intelligence (AI) broadly Read more >
  • On Wednesday, Microsoft shared its aspiration to empower a new Read more >
  • With the new service, developers can accelerate the development of bots with the Microsoft Bot Framework and easily deploy and manage them in a serverless environment on Azure.
  • Microsoft has released an updated version of Microsoft Cognitive Toolkit, Read more >
  • Newly updated Microsoft Cognitive Toolkit can help speed advances in deep learning Photo of Frank Seide standing at the top of a stairway at Microsoft

Harry Shum, Microsoft AI and Research Group executive vice president, and Sam Altman, co-chair of OpenAI. (Photo by Brian Smale)
Continue reading “Advancing our ambition to democratize artificial intelligence”

5 EBooks to Read Before Getting into A Machine Learning Career

#ICYMI 5 EBooks to Read Before Getting into A #MachineLearning Career

  • The Deep Learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general and deep learning in particular.
  • A carefully-curated list of 5 free ebooks to help you better understand the various aspects of what machine learning, and skills necessary for a career in the field.
  • The online version of the book is now complete and will remain available online for free.
  • Sure, many important advancements have been made in machine learning since this was put together, as Nilsson himself says, but these notes cover much of what is still considered relevant elementary material in a straightforward and focused manner.
  • Well, there’s always a collection of tutorials on pursuing machine learning in the Python ecosystem.


A carefully-curated list of 5 free ebooks to help you better understand the various aspects of what machine learning, and skills necessary for a career in the field.

Continue reading “5 EBooks to Read Before Getting into A Machine Learning Career”