How to do dropout regularisation: A Top Deep Learning Trick that’ll Improve Performance for Data Scientists
Proving Gaussian Processes and Neural Networks are equivalent: The Future of Machine Learning is Here
Variational Inference vs MCMC: Variational Inference vs MCMC for Data Scientists
The problems with social media: Thalidomide and the Children of Social Media
Shortcomings of government reporting: Gross Failures in Coronavirus…
Please don’t take any of this for the god’s truth. I’ve been exercising for a while but I have no professional qualifications in nutrition or fitness. Yes I’ve played sport fairly competitively and have spoken to dieticians/nutritionists/physiotherapists extensively, but that’s all personal. The below advice works for me really well, but it may not work for you. In any case, speak to a professional.
I’ve been working from home since March 13 2020.
On the whole it’s been OK but it’s been challenging for sure. …
I’m inquisitive and curious. I want to build tools that customers can use and benefit from. Deployment has always been a tough subject for me because, as far as I can remember, I’ve tried to learn how to make websites, or iPhone applications, or Android applications, but nothing really stuck.
Only until I learned how to deploy Streamlit on Heroku could I actually begin to deploy real projects and actually have potential customers take a look and tell me whether or not they liked the idea. …
Github falls off over the course of holidays as everyone is busy with family but still, coders don’t sleep. We manage to think of problems in the middle of the night and write it down hoping we don’t forget it in the morning.
Github is a phenomenal place as its like stepping into the mind of inquisitive people and seeing the problems they see and the solutions they dream. Its not a perfect land, but when society converges in trying to fix a certain problem, you can see what’s going on.
The following are some of the top
repo’s that I think are pretty cool and useful. Check them out and let me know what you think! …
For those of us with a slight inclination about mathematics and statistics, climate change is
measurable and as such, it’s been proven to be very
Yes, the boundaries within which climate change occurs can be blurry but when we look at the concentration of CO2 in the air, or when we look at the rates of deforestation, we are acutely aware of how bad the environment is changing.
Over the centuries, we’ve polluted and misused Natural Resources which is bringing about grave consequences. …
When we think about
Science, we have to separate our thought into two streams. There’s the
academic side of things, and then there’s the side which is
pragmatic and full of real life experience.
It’s not easy as well. There’s limited
data, sometimes it’s messy and also there’s often
correlation. So as much as people tell you there should be a relationship between X and Y, quite simply, often, there’s just not.
However, to really understand if a phenomenon exists, a few helpful tips and tricks can really push you in the right direction. …
internet is an endeavour that’s interesting, frustrating, challenging and also rewarding.
You can pretty much
scrape anything you want as long as you follow some guidelines on how to scrape with respect:
The reason I say ‘with respect’ is because often, you’ll overdo it and will potentially effect the website you’re scraping, so be mindful of that.
Researchers in particular: the more
data you have, generally speaking the better your
Data Scientists and Machine Learning researchers will both keep a nose around for what’s going on in the community.
I’m a curious individual, so I wanted to see what had been trending this month: all of which I found to be pretty damn interesting.
Here goes it:
The researchers at Facebook have come out with an update to their Pixel-aligned Implicit Function (PIFu) model that aligns pixels of a 2D image with corresponding pixels of a 3D image. Using PIFu, Facebook have made a Deep Learning model (end-to-end) for digitising people, with the ability to infer 3D surface and texture from either a single image, or multiple. …
The ability to format a
string is a pretty basic requirement for anyone that can code, but, there’ve been more than a few ways in the past that you’ve been able to do this in
Python. There’s the original
% method, there’s the
.format method and more recently, there’s the
f-String method. So which do you choose?
I’m pretty lazy so once I got the hang of .
format methods, I kind of stuck to them, but there are drawbacks that I’ll cover which signify the problem with them.
But first, let’s do a quick overview:
This is the classic method, where those who were coding in the early
Python2 days will remember clearly. Essentially you add in a
% score with an ‘s’ (to reflect you want to chuck in a
string) and add the
% sign after the
string as follows. …
NIPS is classed as one of the foremost academic conferences in the space of AI. For academics, being published or running a workshop in this conference is a sign that you’re doing well and you’re making a difference.
The competition to get into this conference is high, like really really high. So generally speaking, you would expect that the best of the best have published the most in it. Let’s look at the most prolific authors who’ve submitted in the NIPS conferences since 1990: