The hard thing about deep learning

The hard thing about #DeepLearning is the #optimization problem

  • In a nutshell: the deeper the network becomes, the harder the optimization problem becomes.
  • To provably solve optimization problems for general neural networks with two or more layers, the algorithms that would be necessary hit some of the biggest open problems in computer science.
  • In the post, I explore the “hardness” in optimizing neural networks and see what the theory has to say.
  • The simplest neural network is the single-node perceptron , whose optimization problem is convex .
  • The reasons for the success of deep learning go far beyond overcoming the optimization problem.


It’s easy to optimize simple neural networks, let’s say single layer perceptron. But, as network becomes deeper, the optmization problem becomes crucial. This article discusses about such optimization problems with deep neural networks.

Continue reading “The hard thing about deep learning”

The hard thing about deep learning

The hard thing about deep learning  #ai

  • In a nutshell: the deeper the network becomes, the harder the optimization problem becomes.
  • The simplest neural network is the single-node perceptron , whose optimization problem is convex .
  • To provably solve optimization problems for general neural networks with two or more layers, the algorithms that would be necessary hit some of the biggest open problems in computer science.
  • There is a rich variety of optimization algorithms to handle convex optimization problems, and every few years a better polynomial-time algorithm for convex optimization is discovered.
  • Judd also shows that the problem remains NP-hard even if it only requires a network to produce the correct output for just two-thirds of the training examples, which implies that even approximately training a neural network is intrinsically difficult in the worst case.

Deeper neural nets often yield harder optimization problems.
Continue reading “The hard thing about deep learning”

Top Ten Intel® Software Developer Stories

What is #MachineLearning and why should you care? It’s everywhere, including the Top Ten:

  • Learn about specific performance problems related to these new technologies.
  • From code samples to how-to guides, we gather the most popular software developer stories in one place each month so you don’t miss a thing.
  • The article explains the various types of machine learning and provides additional resources to get you started.
  • When you add something to your cart in Amazon and see a list of other recommended products that you might also like-that’s an example of machine learning.
  • Learn about the IoT ecosystem, which consists of a broad set of technologies with a common thread of manageability and security.

When you add something to your cart in Amazon and see a list of other recommended products that you might also like—that’s an example of machine learning. This article explains the various types of machine learning and provides additional resources to get you started.
Continue reading “Top Ten Intel® Software Developer Stories”

Must Know Tips/Tricks in Deep Neural Networks

Must Know Tips/Tricks in Deep Neural Networks:  #abdsc #MachineLearning #DeepLearning

  • You need to be a member of Data Science Central to add comments!
  • For more articles about Neural Networks, click .
  • Must Know Tips/Tricks in Deep Neural Networks
  • Deep Neural Networks, especially Convolutional Neural Networks ( CNN ), allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction.
  • They collected and concluded many implementation details for DCNNs.

Read the full article, click here.


@KirkDBorne: “Must Know Tips/Tricks in Deep Neural Networks: #abdsc #MachineLearning #DeepLearning”


This article was posted by Xiu-Shen Wei.  Xiu-Shen Wei is a 2nd-year Ph.D. candidate of Department of Computer Science and Technology in Nanjing University and…


Must Know Tips/Tricks in Deep Neural Networks

Why football, not chess, is the true final frontier for robotic artificial intelligence

#Future #Tech: why #football, not chess, is the true final frontier for #robotic #AI ►

  • In recent years, their ability has significantly improved: many labs now boast five or six-a-side humanoid robot teams .
  • So while the robots may seem less capable this year than the year before, it’s because the goalposts are moving.
  • The tasks involved in playing football, although much more intuitive to humans than chess or Go, are a major challenge for robots.
  • The RoboCup tournament held its 20th competition in Leipzig this year .
  • Led by Hiroaki Kitano and Manuela Veloso , the ambitious goal set that year was to have by 2050 a team of humanoid robots able to play a game of football against the world champion team according to FIFA rules, and win.

Read the full article, click here.


@maximaxoo: “#Future #Tech: why #football, not chess, is the true final frontier for #robotic #AI ►”


Computers must master football if they are to demonstrate that they can be our equal.


Why football, not chess, is the true final frontier for robotic artificial intelligence

Why football, not chess, is the true final frontier for robotic artificial intelligence

Why football, not chess, is the true final frontier for robotic artificial intelligence

  • So while the robots may seem less capable this year than the year before, it’s because the goalposts are moving.
  • The RoboCup tournament reached its 20th year in Leipzig this year .
  • The tasks involved in playing football, although much more intuitive to humans than chess or Go, are a major challenge for robots.
  • It is not in the cerebral boardgames of chess or Go, but on the pitch in the physical game of football that the frontline of life with intelligent robots is being carved out.
  • Led by Hiroaki Kitano and Manuela Veloso , the ambitious goal set that year was to have by 2050 a team of humanoid robots able to play a game of football against the world champion team according to FIFA rules, and win.

Read the full article, click here.


@DeepStuff: “Why football, not chess, is the true final frontier for robotic artificial intelligence”


The perception of what artificial intelligence was capable of began to change when chess grand master and world champion Garry Kasparov lost to…


Why football, not chess, is the true final frontier for robotic artificial intelligence