Deep Learning, TensorFlow and Tensor Core

I was lucky enough to get a ticket to the Google I/O 2017 on a Google Code Jam for Women (for girls that don't know, Google has some programming contest for women and the best classified win tickets to the conference).



One of the main topics of the conference was for sure its new Deep Learning library TensorFlow. TensorFlow is Google's OpenSource Machine Learning library that runs both on CPU and GPU.

Two very cool things were presented at Google I/O:

  •  TPU (Tensor Processing Unit) - a GPU optimized specifically for TensorFlow that can be used on the Google Cloud Engine
  •  TensorFlow Lite - a TensorFlow low weight version to run on Android and make developer's lives easier




Last week, at a BigData meetup in Chicago, I discovered that Nvidia also created a specific GPU hardware for processing Deep Learning, the Tensor Core.

 With all this infrastructure and APIs being made available, Deep Learning can be done considerably easier and faster. At Google I/O, Sundar Pichai mentioned that at Google they have been using Machine Learning for almost everything, and even Deep Learning to train the Deep Learning networks!

TensorFlow's API is so high level, that even someone with little technical background can develop something interesting with it. Sundar also shared a story of a high school guy that used the library to help detecting some types of cancer.

It seems that Data Science is becoming attainable.

Comments

  1. AnonymousAugust 11, 2020 at 10:30 PM

    I was here too - we probably saw each other :)

    ReplyDelete

Post a Comment

Popular posts from this blog

Apache Mahout

Image
“Scalable machine learning library” Mahout is a solid Java framework in the Artificial Intelligence area. It is a machine learning project by the Apache Software Foundation that tries to build intelligent algorithms that learn from some data input. What is special about Mahout is that  it is a scalable library, prepared to deal with huge datasets. Its algorithms are built on top of the Apache Hadoop project and, so, they work with distributed computing. Mahout offers algorithms in three major  areas: Clustering, Categorization and Recommender Systems. This lats part was incoporated in April 4 th 2008, from the previous Taste Recommender System project. Mahout currently implements  a collaborative filtering engine that supports the user-based, item-based and Slope-one recommender systems. Other algorithms available in the package are  the k-means, fuzzy k-Means clustering, Canopy, Dirichlet and Mean-Shift. They also have The Naive Bayes, Complementary Naive Bayes and
Read more

Slope One

Image
Slope One is a simple and efficient type of recommender system. Introduced by Daniel Lemire and Anna Maclachlan in 2005, it involves a simpler idea than the majority of other collaborative filtering implementations. While these usually calculate the similarity between vectors of items using the cosine or the Pearson methods, the Slope One approach recommends items to users based on the average difference in preferences of items.  The main idea of the algorithm is to create a linear relation between items preferences such as the relation F(x) = x + b. The name "Slope One" cames from the fact that here the "x" is multiplied by "1". It basically calculates the difference between the ratings of items for each user (for every item the user has rated). Then, it creates and average difference (diff) for every pair of items. To make a prediction of the Item A for an User 1 for example, it would get the ratings that User 1 has given to other items and a
Read more

Error when using smooth.spline

When trying to interpolate a series of data the cubic spline  is a great technique to be used. I choose to use the smooth.spline function, from the R stats package. > smooth.spline(data$x,  data$y ) Nevertheless, while running smooth.spline on a collection of datasets with different sizes I got the following error: Error in smooth.spline( data$x,  data$y),  :   'tol' must be strictly positive and finite After digging a little bit I discovered that the problem was that some datasets were really small and smooth.spline wasn't being able to compute anything. Hence, make sure your dataset is big enough before applying smooth.spline to it. > if(length(data$x) > 30) {  smooth.spline( data$x,  data$y)  } UPDATE:  A more generalized solution would be: > if(IQR(data$x) > 0) {  smooth.spline( data$x,  data$y)  }
Read more