Robot Cars Can Learn to Drive without Leaving the Garage

.@DeepLearn007 🌀 #Robot Cars Can Learn to Drive without Leaving Garage #AI #DL #autonomous ⏩

  • The researchers tested their system on new images and found that it could discern road features fairly accurately.
  • I am the senior editor for AI at MIT Technology Review .
  • Some video games are now so visually realistic that they can let a computer vision learn about the real world (see ” Self-Driving Cars Can Learn a Lot by Playing Grand Theft Auto “).
  • Researchers at Princeton University recently developed a computer vision and mapping system that gathered useful information about the physical properties of roads by studying Google Street View and comparing the scenes to the information provided in open-source mapping data.
  • The researchers trained their system using 150,000 Street View panoramas.

Playing video games and surfing Google Street View can teach software a lot about driving.
Continue reading “Robot Cars Can Learn to Drive without Leaving the Garage”

Deep Learning Summer School, Montreal 2016

  • Learning to See Learning to See
  • Learning to Communicate with Deep Multi–Agent Reinforcement Learning Learning to Communicate with Deep Multi–Agent Reinforcement Learning
  • Deep Reinforcement Learning Deep Reinforcement Learning
  • The Deep Learning Summer School 2016 is aimed at graduate students and industrial engineers and researchers who already have some basic knowledge of machine learning (and possibly but not necessarily of deep learning) and wish to learn more about this rapidly growing field of research.
  • Learning Deep Generative Models Learning Deep Generative Models

Read the full article, click here.


@karpathy: “Videos from 2016 Deep Learning Summer School in Montreal are up and slides”


Deep neural networks that learn to represent data in multiple layers of increasing abstraction have dramatically improved the state-of-the-art for speech recognition, object recognition, object detection, predicting the activity of drug molecules, and many other tasks. Deep learning discovers intricate structure in large datasets by building distributed representations, either via supervised, unsupervised or reinforcement learning. The Deep Learning Summer School 2016 is aimed at graduate students and industrial engineers and researchers who already have some basic knowledge of machine learning (and possibly but not necessarily of deep learning) and wish to learn more about this rapidly growing field of research. Note: Slide synchronization will soon be added.


Deep Learning Summer School, Montreal 2016

Common Sense in Artificial Intelligence… by 2026?

Common Sense in #ArtificialIntelligence… by 2026?  by @lemire

  • To replace human beings at most jobs, machines need to exhibit what we intuitively call “common sense”.
  • For example, many human beings are illiterate and they can be said to have common sense.
  • Common sense is basic knowledge about how the world of human beings works.
  • For example, if you are lying on the floor yelling “I’m hurt”, common sense dictates that we call emergency services… but it is possible that Apple’s Siri could already be able to do this.
  • If computers could be granted a generous measure of common sense, many believe that they could make better employees than human beings.

Read the full article, click here.


@kdnuggets: “Common Sense in #ArtificialIntelligence… by 2026? by @lemire”


An insightful opinion piece on the future of common sense in AI. A recommended read by an authority in the field.


Common Sense in Artificial Intelligence… by 2026?

Neural Nets in Azure ML – Introduction to Net#

Neural Nets in Azure ML – Introduction to Net#  #ai

  • The network has 3 layers of neurons: an input layer of size 28*28 = 784, one hidden layer of size 100, and the output layer of size 10.
  • You can easily add more layers resulting in a more complex neural network.
  • input Picture [28, 28]; // Note that alternatively we could declare input layer as: // input Picture [28 * 28]; // or just // input Picture [784]; // Net# compiler will be able to infer the number of dimensions automatically.
  • // This defines an output layer of size 10 which is fully-connected to layer ‘H’, // with softmax activation function.
  • The language also supports various types of layers which will be described in subsequent posts.

Read the full article, click here.


@RickKing16: “Neural Nets in Azure ML – Introduction to Net# #ai”


Neural networks are one of the most popular machine learning algorithms today. One of the challenges when using neural networks is how to define a network topology given the variety of possible layer types, connections among them, and activation functions.  Net# solves this problem by providing a succinct way to define almost any neural network architecture in a descriptive, easy-to-read format. This post provides a short tutorial for building a neural network using the Net# language to classify images of handwritten numeric digits in Microsoft Azure Machine Learning. 


Neural Nets in Azure ML – Introduction to Net#