6 areas of AI and Machine Learning to watch closely

#ICYMI 6 areas of #AI and #MachineLearning to watch closely

  • Those who are able to train faster and deploy AI models that are computationally and energy efficient are at a significant advantage.
  • Some have rebranded AI as “cognitive computing” or “machine intelligence”, while others incorrectly interchange AI with “machine learning”.
  • If we want AI systems to solve tasks where training data is particularly challenging, costly, sensitive, or time-consuming to procure, it’s important to develop models that can learn optimal solutions from less examples (i.e. one or zero-shot learning).
  • Deep learning models are notable for requiring enormous amounts of training data to reach state-of-the-art performance.
  • Without large scale training data, deep learning models won’t converge on their optimal settings and won’t perform well on complex tasks such as speech recognition or machine translation.


Artificial Intelligence is a generic term and many fields of science overlaps when comes to make an AI application. Here is an explanation of AI and its 6 major areas to be focused, going forward.

Continue reading “6 areas of AI and Machine Learning to watch closely”

Can a deep net see a cat? – Piekniewski’s blog

Can #deeplearning recognise a cat?  The answer is not obvious. #AI #vision

  • In summary, the thesis of this post is that visual perception is NOT a solved problem and requires more work, likely a fundamental shift.
  • An adversarial example constructed from the category “Egyptian cat” classified with 98% confidence.
  • BTW: since I uploaded these cat images to ClarifAI, they may become part of their training set future results from them might be different than those presented .
  • The “best cat” is quite confidently classified as a dalmatian (0.74) and only with 0.04 confidence as the “Egyptian cat”.
  • It does classify my best cat as a cat (success!

In this post I will explore the capabilities of contemporary deep learning models on the vitally important task of detecting a cat. Not an ordinary cat though, but a sketch of an abstract cat. This task matters because success tells us something about whether a visual system has learned generalization and abstraction  — at least on par with a 2-year old. This post is inspired by my ex co-worker Peter O’Connor who tried similar experiments on LeNet several years ago. In addition, this post is a continuation of this blog’s highly popular “Just how close are we to solving vision?” which to-date has amassed nearly 15,000 hits. Let’s begin by introducing my menagerie:
Continue reading “Can a deep net see a cat? – Piekniewski’s blog”

TensorFlow in a Nutshell  —  Part One: Basics – Medium

TensorFlow in a Nutshell  — Part One: Basics – Medium   #MachineLearning #DeepLearning

  • TensorFlow is a framework created by Google for creating Deep Learning models.
  • tf.zeros() – creates a matrix full of zeros
  • An Operation also referred to as op can return zero or more tensors which can be used later on in the graph.
  • The session run actually causes the execution of three operations in the graph, creating the two constants then the matrix multiplication.
  • any variables or operations used outside of the with new_graph.as_default() will be added to the default graph that is created when the library is loaded.

The fast and easy guide to the most popular Deep Learning framework in the world.

TensorFlow is a framework created by Google for creating Deep Learning m…
Continue reading “TensorFlow in a Nutshell  —  Part One: Basics – Medium”

Multi-Class Classification Tutorial with the Keras Deep Learning Library

Multi-Class #Classification Tutorial with the #Keras #DeepLearning Library #MachineLearning

  • The network uses the efficient ADAM gradient descent optimization algorithm with a logarithmic loss function, which is called categorical_crossentropy in Keras.
  • It ensures that the stochastic process of training a neural network model can be reproduced.
  • In the post you will discover how you can use Keras to develop and evaluate neural network models for multi-class classification problems.
  • The Keras library provides wrapper classes to allow you to use neural network models developed with Keras in scikit-learn.
  • How to evaluate a Keras neural network model using scikit-learn with k-fold cross validation

In this post you will discover how you can use Keras to develop and evaluate neural network models for multi-class classification problems.
Continue reading “Multi-Class Classification Tutorial with the Keras Deep Learning Library”

The Ultimate List of TensorFlow Resources: Books, Tutorials & More

The ultimate list of #TensorFlow Resources: Books, Tutorials, Libraries and more.

  • Colornet – Neural Network to colorize grayscale images – Neural Network to colorize grayscale images
  • TensorFlow Tutorial 2 – Introduction to deep learning based on Google’s TensorFlow framework.
  • Globally Normalized Transition-Based Neural Networks – This paper describes the models behind SyntaxNet .
  • Highway Network – Tensorflow implementation of “Training Very Deep Networks” with a blog post
  • TensorFlow: A system for large-scale machine learning – This paper describes the TensorFlow dataflow model in contrast to existing systems and demonstrate the compelling performance

A curated list of 50+ awesome TensorFlow resources including tutorials, books, libraries, projects and more.
Continue reading “The Ultimate List of TensorFlow Resources: Books, Tutorials & More”

TensorFlow in a Nutshell  —  Part One: Basics – Medium

TensorFlow in a Nutshell - The Basics for Beginners. #MachineLearning #Python #AI

  • An Operation also referred to as op can return zero or more tensors which can be used later on in the graph.
  • tf.zeros() – creates a matrix full of zeros
  • TensorFlow is a framework created by Google for creating Deep Learning models.
  • The session run actually causes the execution of three operations in the graph, creating the two constants then the matrix multiplication.
  • any variables or operations used outside of the with new_graph.as_default() will be added to the default graph that is created when the library is loaded.

Read the full article, click here.


@Mybridge: “TensorFlow in a Nutshell – The Basics for Beginners. #MachineLearning #Python #AI”


TensorFlow in a Nutshell — Part One: Basics

The fast and easy guide to the most popular Deep Learning framework in the world.

TensorFlow is a framework c…


TensorFlow in a Nutshell  —  Part One: Basics – Medium

Lighting the way to deep machine learning

Lighting the way to deep #MachineLearning #DataScience

  • The data set iterator receives as input a closure that constructs the Torchnet data set object.
  • Torchnet provides a framework on top of a deep learning framework (in this case, torch/nn ) that makes rapid experimentation easier.
  • For instance, small subpackages that wrap vision data sets such as the Imagenet and COCO data sets, speech data sets such as the TIMIT and LibriSpeech data sets, and text data sets such as the One Billion Word Benchmark and WMT-14 data sets.
  • Although machine learning and artificial intelligence have been around for many years, most of their recent advances have been powered by publicly available research data sets and the availability of more powerful computers – specifically ones powered by GPUs.
  • The modular Torchnet design makes it easy to test a series of coding variants focused around the data set, the data loading process, and the model, as well as optimization and performance measures.

Read the full article, click here.


@MikeTamir: “Lighting the way to deep #MachineLearning #DataScience”


Building rapid and clean prototypes for deep machine-learning operations can now take a big step forward with Torchnet, a new software toolkit that fosters rapid and collaborative development of deep learning experiments by the Torch community.


Lighting the way to deep machine learning