Will AI Replace Radiologists?



Ever since Geoffrey Hinton, who is considered the father of deep learning, said in a conference of radiologists that the field will soon be taken over by AI(Artificial Intelligence), a huge debate has erupted among radiologists and AI experts, whether this is a possibility in the foreseeable future or not.
If we look closely, the answer is clearly; No. Radiologists will not be replaced by AI systems. However, the nature of the job of radiologists will change.
The reason why there is confusion in the first place is that radiology(majorly) is a branch of medicine. And medicine is largely misunderstood beyond the practitioners of this field. Furthermore, there are very few people in the world who have a good knowledge of both AI and medicine and also statistical inference associated with it.
In classical texts, medical diagnosis is always described as a protocol where a set of procedures are followed…

View original post 1,019 more words


Sample Size Estimation for Machine Learning Models Using Hoeffding’s Inequality


Wassily Hoeffding (1914 -1991) was one of the founding fathers of non- parametric statistics (picture credit: http://stat-or.unc.edu)

Deep learning is the talk of town these days and with advent of frameworks like Tensorflow, Keras and SciKitlearn etc. anyone can implement it with ease. This is why the first hunch of everyone when dealing with data is to someway apply deep learning to it or at-least some form of machine learning. However, what most of us don’t realize is that; to have a theoretical guarantee over learning and and then testing in such a way that error is minimized when the model is deployed in the real-world, we need considerably large data sets. And such large data sets are very hard to get.

This theoretical guarantee is of utmost importance when dealing with medical or health related data because to generate confidence intervals (values between which your point predictors in-sample can…

View original post 467 more words

How to configure local computer for FastAI course

Code Yarns 👨‍💻

I wanted to check out the Practical Deep Learning for Coders course by FastAI. However, I noticed that the course provided configuration instructions mainly for cloud GPU instance providers like Paperspace. I have a notebook and a desktop computer with powerful NVIDIA GPUs and wanted to try the course on my local machines. The course material is also provided in the form of Jupyter notebooks, while I intended to turn those into Python programs to run locally.

Here are the steps I followed to get my local computer setup for the FastAI course:

  • The local computer was running Ubuntu 16.04 and NVIDIA drivers were already installed on it and working.
  • CUDA 9.0 was installed using the online instructions from NVIDIA.
  • The latest release of CuDNN was installed as described here.
  • Conda was installed and configured as described here. You should be able to run conda info from…

View original post 149 more words

A Step by Step Backpropagation Example

Matt Mazur


Backpropagation is a common method for training a neural network. There is no shortage of papers online that attempt to explain how backpropagation works, but few that include an example with actual numbers. This post is my attempt to explain how it works with a concrete example that folks can compare their own calculations to in order to ensure they understand backpropagation correctly.

If this kind of thing interests you, you should sign up for my newsletter where I post about AI-related projects that I’m working on.

Backpropagation in Python

You can play around with a Python script that I wrote that implements the backpropagation algorithm in this Github repo.

Backpropagation Visualization

For an interactive visualization showing a neural network as it learns, check out my Neural Network visualization.

Additional Resources

If you find this tutorial useful and want to continue learning about neural networks, machine learning, and…

View original post 1,794 more words

Alan Turing’s Patterns in Nature, and Beyond from Wired Magazine


I found this ‘Interesting’ article on wired.com and was filled with some sort of an inexplicable joy. The buzzkill, however was that I had to click on each photograph to read about it. Hence this post…

This originally appeared in http://www.wired.com on February 22, 2011 at 7:00 am and is written by Brandon Keim.

Thanks Brandon Keim…

Alan Turing’s Biology PaperImage

Near the end of his life, the great mathematician Alan Turing wrote his first and last paper on biology and chemistry, about how a certain type of chemical reaction ought to produce many patterns seen in nature.

Called “The Chemical Basis of Morphogenesis,” it was an entirely theoretical work. But in following decades, long after Turing tragically took his own life in 1954, scientists found his speculations to be reality.

First found in chemicals in dishes, then in the stripes and spirals and whorls of animals…

View original post 974 more words

Camels in the Cambrian? A Geology Mnemonic

Life in Pen and Ink

Sitting camel

How did you learn the geological timescale?

Geology is not a standard subject in the UK Curriculum, so those few students who arrive at university having done it at GCSE or A-Level, have usually been taught it by non-tradtitional means.  They are more exposed to the whim and wit of their teacher than they would be in any other subject.

In fact, it was partly the charisma and enthusiasm of my A-Level Geology teacher that prompted me to apply to Geology at university, and…well, the rest is history.  Initially planning to take science subjects and apply for biochemistry, I chose Geology at A-Level on a bit of a whim – having always enjoyed physical geography.  Imperceptibly, as the weeks passed, all thoughts of biochemistry slipped away, and I realised I’d been a geologist all along.  Starting it at university was a bit of a shock to the system, and it…

View original post 364 more words

Siamese Cats and the Optic Chiasm

the sensitive motor

Anatomy constrains function | Function drives anatomy

As a general rule of thumb, information about the right side of the body is represented in the left side of the brain, and information about the left side is represented on the right.  This is called lateralization.  While that’s probably only mildly interesting to most people, it can help neurologists determine where a nervous system injury (eg, stroke) has occurred.

But to me, even though I study the motor and somatosensory systems where this holds (mostly) true, I think a cooler example of decussation (crossing from one side to the other) is the optic chiasm.   More than that, it’s a great example of what neuroanatomy can tell us about the body and how it functions in its environment.  Similarly, the anatomy and behavior of an animal tell us about its brain.

Before I get in to the details, I should cover a few terms: visual fields, monocular/binocular…

View original post 1,118 more words