The machine learning industry moves at the speed of innovation. Daily developments and progress pushes the frontier of ML and AI just that bit further.
As a practising machine learning engineer, it can be challenging to keep up with the pace of developments that occurs within the industry. I find that complacency, even for a short period, can set you back months or years behind the frontier of ML.
This article details some of the steps I’m taking in 2021 to stay relevant to the industry in terms of expertise and general domain knowledge. …
What does it take to understand Computer Vision, Deep Learning and AI?
For me, it took one year of exploring machine learning, another year undertaking an MSc in Computer Vision, Machine Learning and Robotics, and finally just under two years of working as a professional Computer Vision Engineer.
And to be honest, there’s still a lot for me to uncover and learn within the field of Machine learning and the AI industry in general.
That been said, you don’t have to spend years grasping the foundations of machine learning. …
This article is an exploration into a specific segment within the wonderful field of Machine Learning(ML). You should come away from this article with one of the following: a newfound enthusiasm to explore an area of machine learning that might be new to you, or a new friend you share similar interests with.
The first organism began to observe its environment through visual perception approximately 500 million years ago. Today, we have artificial machines and cameras able to derive scenic understanding from the input data fed into their optical or remote sensors. …
Deep learning is a machine learning field that utilises artificial neural networks(ANNs) to learn patterns from data.
A rudimentary explanation to the way deep learning works is that the ANNs attempt to mimic, in some form, how the human brain functions (although this will be oversimplifying how it works).
One supposable limiting factor of artificial neural networks is that they are utilised for solving tasks that share a close association (similar patterns)with the data used to train the ANNs.
The key benefit of deep learning is that the learning process and feature extraction within deep learning architectures occurs automatically. There…
The truth is you will make tons of mistakes in your career as an ML practitioner. The plus side is that there’s an opportunity to learn and level up for each mistake you make.
In this article, you’ll come across mistakes that I’ve made so far in my career as a Computer Vision / Machine Learning Engineer; and how you as an ML practitioner can avoid each mistake I’ve made.
The average human spends 50 years of their entire lives employed in a job, and for most of us, we are just at the start of our careers, furthermore, I…
Understand convolutional neural network receptors and pooling techniques.
Receptive fields are defined portions of space or spatial construct containing units that provide input to a set of units within a corresponding layer.
The receptive field is defined by the filter size of a layer within a convolution neural network. The receptive field is also an indication of the extent of the scope of input data a neuron or unit within a layer can be exposed to (see image below).
The local receptive field is a defined segmented area that is occupied by the content of input data that a neuron…
Productivity is not a destination, it’s a journey.
The simple realisation that productivity is not a destination, goal or target but rather, a journey that’s approached at varying speeds allows us to accept the common shortcomings that we will encounter as we maximise our productivity.
The Machine Learning discipline is concerned with the optimisation and automation of processes. I find myself retraining machine learning models with different hyperparameters to squeeze out small unit accuracy. And if I encounter a repetitive task in any of my daily activities, my brain immediately works on ways of automating the manual process.
Teaching is the best form of learning; someone once said, not sure who.
Ever since I took my very first online course on Machine Learning taught by none other than Andrew Ng, I’ve been very eager to inform my colleagues and people about what I’ve learnt.
Relaying all information I got from my learnings back to curious individuals who wanted to know more about ML and AI techniques, improved my understanding of ML topics.
Fast forward to a couple of years later, and I’m still communicating information on what I’m currently studying. This time I’m not only telling people face…
If there is one book you should purchase to be prepared for machine learning in realistic environments, then Hands-On Machine Learning by Aurélien Géron is the holy grail for practical machine learning.
Most readers will have come across this book or its previous editions.
The book contains two parts.
The first part introduces typical machine learning concepts and techniques such as gradient descent, support vector machines, feature engineering, and many more. The first part also introduces SciKit-Learn, a popular machine learning library, along with some common visualization and wrangling tools.