An Overview of Python Deep Learning Frameworks

#ICYMI An Overview of #Python #DeepLearning Frameworks

  • 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.
  • Since Theano aims first and foremost to be a library for symbolic mathematics, Lasagne offers abstractions on top of Theano that make it more suitable for deep learning.
  • Similar to Lasagne, Blocks is a shot at adding a layer of abstraction on top of Theano to facilitate cleaner, simpler, more standardized definitions of deep learning models than writing raw Theano.
  • More recently, the TensorFlow team decided to incorporate support for Keras, the next deep learning library on our list.
  • It’s a loose port of Lua’s Torch library to Python, and is notable because it’s backed by the Facebook Artificial Intelligence Research team (FAIR), and because it’s designed to handle dynamic computation graphs — a feature absent from the likes of Theano, TensorFlow, and derivatives.


Read this concise overview of leading Python deep learning frameworks, including Theano, Lasagne, Blocks, TensorFlow, Keras, MXNet, and PyTorch.

Continue reading “An Overview of Python Deep Learning Frameworks”

Artificial Intelligence Is Changing How We Shop Online

How #AI is changing the way we do our shopping online:

  • These deep learning algorithms have been used in the autonomous driving industry for quite some time, and only now is it beginning to branch out into other industries, such as online shopping.
  • One company that offers machine learning solutions for e-commerce businesses and others is Adobe Marketing Cloud as they recognize the need to make use of AI as early as possible.
  • Andrew Zhai is an engineer working on the visual search side of things at Pinterest, and he said, “For shopping specifically, improvements to online discovery means new ways to find products you’re interested in but may not have the words for.
  • Etsy is also keen to jump onboard with deep learning technology, and just last fall purchased Blackbird Technologies to integrate the firm image recognition and natural language processing into its search function.
  • Some of Adobe’s marketing tools also use deep learning techniques and are used to predict their customer’s shopping behaviors and patterns.

There’s no doubt about it that our future is one that involves artificial intelligence (AI) in a big way. While some companies are faster than others at
Continue reading “Artificial Intelligence Is Changing How We Shop Online”

An Overview of Python Deep Learning Frameworks

#ICYMI An Overview of #Python #DeepLearning Frameworks

  • 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.
  • Since Theano aims first and foremost to be a library for symbolic mathematics, Lasagne offers abstractions on top of Theano that make it more suitable for deep learning.
  • Similar to Lasagne, Blocks is a shot at adding a layer of abstraction on top of Theano to facilitate cleaner, simpler, more standardized definitions of deep learning models than writing raw Theano.
  • More recently, the TensorFlow team decided to incorporate support for Keras, the next deep learning library on our list.
  • It’s a loose port of Lua’s Torch library to Python, and is notable because it’s backed by the Facebook Artificial Intelligence Research team (FAIR), and because it’s designed to handle dynamic computation graphs — a feature absent from the likes of Theano, TensorFlow, and derivatives.


Read this concise overview of leading Python deep learning frameworks, including Theano, Lasagne, Blocks, TensorFlow, Keras, MXNet, and PyTorch.

Continue reading “An Overview of Python Deep Learning Frameworks”

Deep Learning with MATLAB: Transfer Learning in 10 Lines of MATLAB Code Video

Watch this 4 minute video and learn to use #deeplearning with your own data.

  • Watch a quick demonstration of how to use MATLAB® for transfer learning which is a practical way to apply deep learning to your problems.
  • This demo teaches you how to use transfer learning to re-train AlexNet, a pretrained deep convolutional neural network (CNN or ConvNet) to recognize snack food such as hot dogs, cup cakes and apple pie.

“Learn how to use transfer learning in MATLAB to re-train deep learning networks created by experts for your own data or task. ”
Continue reading “Deep Learning with MATLAB: Transfer Learning in 10 Lines of MATLAB Code Video”

Create Realistic Synthetic Faces That Look Older With Deep Learning – News Center

New face aging #AI system can help identify people who have been missing for decades.

  • Developers from Orange Labs in France developed a deep learning system that can quickly make young faces look older, and older faces look younger.
  • Using CUDA, Tesla K40 GPUs and cuDNN for the deep learning work, they trained their neural network on 5,000 faces from each age group (0-18, 19- 29, 30-39, 40-49, 50-59, and 60+ years old) taken from the Internet Movie Database and from Wikipedia and then labeled with the person’s age — this helped the system learn the characteristic signature of faces in each age group.
  • A second neural network, called the face discriminator, looks at the synthetically aged face to see whether the original identity can still be picked out.
  • If it can’t, the image is rejected, which they call the process in their paper, Age Conditional Generative Adversarial Network.
  • Grigory Antipov of Orange Labs mentioned the technique could be used in applications such as helping identify people who have been missing for many years.

Developers from Orange Labs in France developed a deep learning system that can quickly make young faces look older, and older faces look younger. A number of techniques already exist, but they are expensive and time consuming.
Continue reading “Create Realistic Synthetic Faces That Look Older With Deep Learning – News Center”

Using TensorFlow in Windows with a GPU

Using #TensorFlow in @Microsoft #Windows with a #GPU  #DeepLearning

  • Particularly, I was curious about my Windows Surface Book (GPU: GeForce GT 940) performance of using the GPU vs the CPU.
  • When TensorFlow was first released (November 2015) there was no Windows version and I could get decent performance on my Mac Book Pro (GPU: NVidia 650M).
  • Read here to see what is currently supported The first thing that I did was create CPU and GPU environment for TensorFlow.
  • To create my CPU TensorFlow environment, I used:

    To create my CPU TensorFlow environment, I used:

    Your TensorFlow code will not change using a single GPU.

  • You can switch between environments with:

    If you are doing moderate deep learning networks and data sets on your local computer you should probably be using your GPU.

In case you missed it, TensorFlow is now available for Windows, as well as Mac and Linux. This was not always the case. For most of TensorFlow’s first year…
Continue reading “Using TensorFlow in Windows with a GPU”

Deep Learning Research Review: Natural Language Processing

#ICYMI #DeepLearning Research Review: Natural Language Processing  #NLP

  • Since deep learning loves math, we’re going to represent each word as a d-dimensional vector.
  • Extracting the rows from this matrix can give us a simple initialization of our word vectors.
  • The above cost function is basically saying that we’re going to add the log probabilities of ‘I’ and ‘love’ as well as ‘NLP’ and ‘love’ (where ‘love’ is the center word in both cases).
  • One Sentence Summary: Word2Vec seeks to find vector representations of different words by maximizing the log probability of context words given a center word and modifying the vectors through SGD.
  • Bonus: Another cool word vector initialization method: GloVe (Combines the ideas of coocurence matrices with Word2Vec)


This edition of Deep Learning Research Review explains recent research papers in Natural Language Processing (NLP). If you don’t have the time to read the top papers yourself, or need an overview of NLP with Deep Learning, this post is for you.

Continue reading “Deep Learning Research Review: Natural Language Processing”