Cross validation is a technique commonly used In Data Science. Most people think that it plays a small part in the data science pipeline, i.e. while training the model. However, it has a broader application in model selection and hyperparameter tuning.

Let us first explore the process of cross validation itself and then see how it applies to different parts of the data science pipeline

Cross-validation is a resampling procedure used to evaluate machine learning models on a…

As a teacher of Data Science (Data Science for Internet of Things course at the University of Oxford),  I am always fascinated in cross connection between concepts. I noticed an interesting image on Tess Fernandez slideshare (which I very much recommend you follow) which talked of…

Understanding the maths behind forward and back propagation is not very easy.

There are some very good – but also very technical explanations.

For example : The Matrix Calculus You Need For Deep Learning Terence Parr and Jeremy Howard is an excellent resource but still too complex for beginners. 

I found a much simpler explanation in the ml cheatsheet.

The…

Introduction

Automated machine learning is a fundamental shift to machine learning and data science. Data science as it stands today, is resource-intensive, expensive and challenging. It requires skills which are in high demand. Automated Machine learning may not quite lead to the beach lifestyle for the data…

At the Data Science for IoT course at the University of Oxford – I have been working on a strategy implementing Artificial Intelligence holistically on the Cloud and Edge. This is a complex approach with many new concepts to learn.…

In this post, I explain

1. How you can participate further in the free book series which we are launching based on the early experiences and
2. Useful resources we recommend based on our experience for learning coding for Data Science (using Python – tensorflow and keras)

To provide some context, I posted…

Introduction

“The question  is not whether intelligent machines can have any emotions, but whether machines can be intelligent without any emotions”. 

Marvin Minsky

The ability of AI to recognise emotions is a fascinating subject and has wide-ranging applications across many fields of…

Background

One of the hardest problem in AI is not technical

It is social

Specifically, it is the problem of “educating people for living and working in a world dominated by AI”

This blog is based on my talk and notes in panels at the…

AI and patents - trends to watch  from the WIPO technology trends report

WIPO Technology Trends report 2019  came as a surprise to me. We in AI are not used to thinking about patents so much because tools / platforms are mostly Open sourced.

Here are the key…

Introduction

I spoke at the iot expo on AI and smart cities  in London this week

Smart cities have been around for more than a decade

The overall numbers for Smart cities are promising

• 2018 over $81 billion was spent on Smart City initiatives and this number is expected…

Background

When I was teaching a session on AI at an MBA program at the London School of Economics,   I thought of explaining AI from the perspective of the life-cycle of Data. This explanation is useful because more people are used to data (than to code). I welcome comments on this approach. Essentially, we consider how data is used and transformed for AI and what are its…

Introduction

This blog is a part of the learn machine learning coding basics in a weekend . We recommend the book Python Data Science Handbook by Jake…

For background to this post, please see Learn #MachineLearning Coding Basics in a weekend. Here,we present the glossary that we use for the coding and the mindmap attached to these classes and upcoming book. …

image source - wikipedia

UPDATE

Hello all

we are now closing this 

we have been…

After a recent webinar, I was asked about advice for getting a job in AI for a fresh graduate

This is a good question and not often answered

Here are my thoughts

Background

• Firstly, AI is a vast topic. Everyone has a limited view on AI based on their personal…

Note: This is a long post, but I kept it as a single post to maintain continuity of the thought flow

In this longish post, I have tried to explain Deep Learning starting from familiar ideas like machine learning. This approach forms a part of my forthcoming book. You can connect with me on Linkedin to know more about the book. I have used this approach in my teaching. It is based on ‘learning by…

Most of us start working with specific programming languages like TensorFlow and Pyspark

So, we are relatively not so used to working with Cloud APIs.

But Cloud APIs for Machine Learning and Deep Learning can make your life a lot easier in building AI and Machine Learning services

Of course, the Cloud APIs have a cost – but they…

Geoffrey Hinton dismissed the need for explainable AI. A range of experts have explained why he is wrong.

I actually tend to agree with…

Introduction

In this post, I explain the maths of Deep Learning in a simplified manner.  To keep the explanation simple, we cover the workings of the MLP mode (Multilayer Perceptron). I have drawn upon a number of references – which are indicated in the post in the relevant sections.

Deep Learning models are playing a significant role in many domains. In the simplest case, deep learning involves stacking multiple neural network layers to address a…

Introduction

Exploratory Data Analysis (EDA) is an approach/philosophy for data analysis that employs a variety of techniques (graphical and quantitative) to better understand data. It is easy to get lost in the visualizations of EDA and to also lose track of the purpose of EDA. EDA aims to make the downstream analysis easier.…