Unlike more traditional monolithic DL networks, PathNet reuses a network that consists of many neural networks and trains them to perform multiple tasks. In the authors experiments, they have shown that a network trained on a second task learns faster than if the network was trained from scratch. This indicates that transfer learning (or knowledge reuse) can be leveraged in this kind of a network. PathNet includes aspects of transfer learning, continual learning and multitask learning. These are aspects that are essential for a more continuously adaptive network and thus an approach that may lead to an AGI (speculative).

Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only global structure and discards information about detailed texture. In this paper, we present a simple but principled method to learn such global representations by combining Variational Autoencoder (VAE) with neural autoregressive models such as RNN, MADE and PixelRNN/CNN. Our proposed VAE model allows us to have control over what the global latent code can learn and , by designing the architecture accordingly, we can force the global latent code to discard irrelevant information such as texture in 2D images, and hence the VAE only "autoencodes" data in a lossy fashion. In addition, by leveraging autoregressive models as both prior distribution $p(z)$ and decoding distribution $p(x|z)$, we can greatly improve generative modeling performance of VAEs, achieving new state-of-the-art results on MNIST, OMNIGLOT and Caltech-101 Silhouettes density estimation tasks.

I recently stumbled across an old Data Science Stack Exchange answer of mine on the topic of the "Best Python library for neural networks", and it struck me how much the Python deep learning ecosystem has evolved over the course of the past 2.5 years. The library I recommended in July 2014,, is no longer actively developed or maintained, but a whole host of deep learning libraries have sprung up to take its place. Each has its own strengths and weaknesses. We've used most of the technologies on this list in production or development at indico, but for the few that we haven't, I'll pull from the experiences of others to help give a clear, comprehensive picture of the Python deep learning ecosystem of 2017. Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently.

The British Artificial Intelligence (AI) company DeepMind Technologies, a subsidiary of Google, recently revealed it will be utilizing a blockchain technology. The firm will use a distributed ledger application to better secure patient data. DeepMind is a software firm that builds algorithms for simulations, applications, and gaming protocols. The company is well known for creating a machine learning platform that learns how to play video games. DeepMind has also built a Neural Turing Machine which mimics a human's short-term memory.

Schedule and Syllabus Unless otherwise specified the course lectures and meeting times are: Wednesday, Friday 3:30-4:20 Location: 200-219 This syllabus is subject to change according to the pace of the class.

The insideBIGDATA Guide to Deep Learning & Artificial Intelligence is a useful new resource directed toward enterprise thought leaders who wish to gain strategic insights into this exciting area of technology. In this guide, we take a high-level view of AI and deep learning in terms of how it's being used and what technological advances have made it possible. We also explain the difference between AI, machine learning and deep learning, and examine the intersection of AI and HPC. We present the results of a recent insideBIGDATA survey that reflects how well these new technologies are being received. Finally, we take a look at a number of high-profile use case examples showing the effective use of AI in a variety of problem domains.

It is no mystery why poker is such a popular pastime: the dynamic card game produces drama in spades as players are locked in a complicated tango of acting and reacting that becomes increasingly tense with each escalating bet. The same elements that make poker so entertaining have also created a complex problem for artificial intelligence (AI). A study published today in Science describes an AI system called DeepStack that recently defeated professional human players in heads-up, no-limit Texas hold'em poker, an achievement that represents a leap forward in the types of problems AI systems can solve. DeepStack, developed by researchers at the University of Alberta, relies on the use of artificial neural networks that researchers trained ahead of time to develop poker intuition. During play, DeepStack uses its poker smarts to break down a complicated game into smaller, more manageable pieces that it can then work through on the fly.

High-performance graphics cards, typically associated with gaming, have become popular over the last few years in an area many might not expect: artificial intelligence. Many experts attribute recent acceleration of success in AI to a wider availability and use of graphics processing units (GPUs), as their advantages include cores designed for running multiple tasks simultaneously, which can efficiently handle the vector and matrix operations that are prevalent in deep learning. Training and deploying state of the art deep neural networks is very computationally intensive, and, while modern GPUs offer high density computation, researchers need more than a fast processor -- they also need optimized libraries, and tools to efficiently program so that they can experiment with new ideas. Bryan Catanzaro, VP of Applied Deep Learning Research at NVIDIA, joined us at the 2017 Deep Learning Summit in San Francisco, to share expertise on GPUs and platforms for deep learning, as well as giving insights on the latest deep learning developments at NVIDIA. I asked him some questions at the summit to learn more about his work. What motivated you to begin your work in deep learning?

Despite the introduction of all sorts of new technology, a myriad of new channels and a host of self-service options, when things go wrong, get complicated or become difficult for customers most of them will want to pick up the phone and talk to another human being. That behaviour makes phone conversations an integral and hugely important part of the whole customer experience, whether the conversations take place at the beginning (sales), middle (service) or the end (renewal) of the customer's journey. However, the problem with phone conversations is that they don't always go as well as companies or customers would like. And, following a phone conversation it's not uncommon to hear phrases like: "It felt like they were more interested in selling me something rather than fixing my problem" So, in the midst of all the new and exciting technology that is emerging, it's exciting to see some technologists turning their attention to phone conversations and how companies can use advanced technology like artificial intelligence (AI), behavioural science, analytics and deep learning to help companies improve the conversations they have with their customers. Here are a couple of examples of two firms that I have come across in the last few weeks that are using advanced technology, in different ways and at different parts of the customer journey, to help improve conversations with customers.

For a brief moment last spring, the world was looking at artificial intelligence because it beat the world champion at Go, the ancient game that was long thought to be unplayable by A.I. because it requires human-like contextual thinking to win. On Thursday, news of a documentary about that moment was announced and will show at New York's Tribeca Film Festival at the end of April. The film is directed by Greg Kohs and follows the story of how the Google DeepMind team played through the go tournament and beat Lee Sedol -- the world's best go player who had dominated the international field for the last decade. With simple rules but a near-infinite number of possible outcomes, the ancient Chinese board game go has long been considered the holy grail of artificial intelligence. Director Greg Kohs' absorbing documentary chronicles Google's DeepMind team as it takes on one of the world's top go players in a weeklong tournament, pitting man against machine in a competition that reveals as much about the workings of the human mind as it does the future of A.I. Go sounds like a simple game -- two players place different colored stones on a checkered board, trying to capture their opponent's stones by surrounding them with nine of their own.