This 2019 year in review is an exercise in looking back and seeing how much has changed in just this one year alone. While I did manage to accomplish a few things, It is the things that I didn’t plan ahead that brought me the greatest sense of fulfillment and the most interesting conversations. I wish this exercise helps me recognize accomplishments as well as setbacks.

Image for post
Image for post
Muir woods

Writing

I had the privilege of writing 2 technical articles this year. I was not able to write as much as I would have loved to.


U-nets yielded better image segmentation in medical imaging. U-Net: Convolutional Networks for Biomedical Image Segmentation paper was published in 2015.

Problem

There is large consent that successful training of deep networks requires many thousand annotated training samples. The paper presents a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently.

The typical use of convolutional networks is on classification tasks, where the output to an image is a single class label. However, in many visual tasks, especially in biomedical image processing, the desired output should include localization i.e. a…


ResNets created major improvements in accuracy in many computer vision tasks. Deep Residual Learning for image recognition was published in 2015.

Problem

Adding more layers leads to the model’s accuracy saturating, then rapidly decaying, and higher training errors — the degradation problem.

Driven by the significance of network depth, a question arose: Is learning better networks as easy as stacking more layers? An obstacle to this question was the vanishing/exploding gradients problem.

Image for post
Image for post
Adding more layers to a suitably deep model leads to higher training error.

The degradation of the training accuracy indicates that not all systems are similarly easy to optimize. Considering a shallower architecture and its deeper counterpart that adds more layers onto…


This blog post series will be updated as I have a second take on the fast ai lessons. These are my personal notes; a strive to understand things clearly and explain them well. Nothing new, only living up this blog.

Fast.ai takes the approach of “here is how to use the software to do something then looks behind the scenes by looking at the details.”

Dropout

learn = ConvLearner.pretrained(arch, data, ps=0.5, precompute=True)

precompute=True precomputes the activations that come out of the last convolutional layer. An activation is a number calculated based on some weights also known as parameters that make up…


This blog post series will be updated as I have a second take on the fast ai lessons. These are my personal notes; a strive to understand things clearly and explain them well. Nothing new, only living up this blog.

Quick Dogs Vs Cats

Here is an end to end process to get a state of the art result for dogs vs. cats:

Image for post
Image for post
PATH = "data/dogscats/"

We assume that your data is in the data folder. But you may want to put them somewhere else. In that case you use symbolic link or symlink for short.


This blog post series will be updated as I have a second take on the fast ai lessons. These are my personal notesm a strive to understand things clearly and explain them well. Nothing new, only living up this blog.

Lesson 1 review

We used three lines of code to build an image classifier:

The organisation of data under PATH involves a train folder and valid folder. Under each of these folders are classification labels i.e. cats and dogs with corresponding images in them.

The training output: [epoch number , training loss, validation loss,accuracy]

0      0.157528   0.228553   0.927593

Choosing a good learning rate

The learning rate decide how…


This blog post series will be updated as I have a second take on the fast ai lessons. These are my personal notes, a strive to understand things clearly and explain them well. Nothing new, only living up to this blog.

I will be renting Paperspace GPUs (graphical processing units) to train neural networks as the cost seem quite affordable. Specifically, we will be using Nvidia GPU as they support CUDA.

fast.ai requires python 3

A brief recap on Fast ai

Fast ai is built on top of pytorch which is a deep learning library built by Facebook. The library…


If you want to master something, teach it. — Richard Feynman

TLDR: writing as proof of work

Image for post
Image for post

This blog post won’t be long. I don’t intend to waste your time by telling you why I do things the way I do them as my circumstances are definitely different from yours.

I started on Data Science as a hobby then found myself spending most of my time on it. This goes without saying that most of the skills I’ve since acquired are self-taught. The approach I took was breadth first then depth.

The plan was to first get basic working knowledge…


With the kickoff of the 2018 FIFA World Cup fast approaching, every soccer fan in the world is dying to know: Who will capture the coveted trophy?

If you’re not just a soccer fan but also a techie, I guess you have realized that Machine Learning and Artificial Intelligence are presently buzzwords too. Let us combine these two to predict which country will win the FIFA World Cup.

Image for post
Image for post

Disclaimer: This should in no way be used for betting or any financial decision. Should you choose to, who am I to stop you.(just …


I set out to use linear regression to predict housing prices in Iowa.I will be highlighting how I went about it, what worked for me, what didn’t and what I learnt in that process.

Image for post
Image for post

First what is the problem?

The problem is to build a model that will predict house prices with a high degree of predictive accuracy given the available data. More about it here. “With 79 explanatory variables describing (almost) every aspect of residential homes in Ames, Iowa, this competition challenges you to predict the final price of each home.”

Where I got the data

The dataset is the prices and features of…

Gerald Muriuki

Contrarian

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store