Another dot in the blogosphere?

Posts Tagged ‘youtube

It is easy to watch this video and walk away assuming that taking handwritten notes is better than typing them.

Video source

If you do, you probably did not watch the video all the way though or pay attention to what matters in note-taking.

The important message of research on note-taking it this: It’s not WHAT you use, it’s HOW you use it.

It does not matter if you prefer to take notes by handwriting or by typing. It is how you attempt to quickly process what you see and hear before you record it. It is about your ability to analyse and summarise.

See the world as it is… and defy it. -- Satya Nadella, Microsoft CEO

I got the quote above from this interview.

Taken out of context, the words of Satya Nadella, the Microsoft CEO, might sound like a call for chaos.

Change might resonate or disrupt. But it rarely starts with getting permission first. It often starts with defiance to norms that feel wrong or could be elevated.

Today I focus on BTS. No, not that BTS. Behind-the-scenes, BTS.

I not only like to get insights on the processes behind the product, I also like to see the people responsible for both.

Video source

Great Big Story is one of my favourite YouTube channels. My family and I watch at least one of their videos practically every day. The channel is informative and inspiring.

Before watching this special focus, I did not realise how many women made the videos behind-the-scenes. Now I see why they offer so much quality.

Video source

Before I forget, I should post this video about how we remember. It is about how we forget in order to remember.

I am glad I remembered before I forgot to share this. Yes, facilitating day and night classes takes a toll…

Video source

When AI does unsupervised learning, it does so without training labels or known answers. People do this all the time, e.g., observing and mimicking the behaviour of others.

A key strategy for AI is creating categories and patterns for new or unknown entities. This is called unsupervised clustering. To create categories, AI must know what to measure and how to represent it.

The video helps make this overall process clearer with examples of image recognition, i.e., grouping similar looking flowers into its own species group, and differentiating unlabelled images.

While this video focused on the basics of imaging with AI, the next promises to focus on natural language processing.

Video source

This video provides some insights into why we seem to have a negative bias when it comes to news.

We are wired to pay more attention to bad news. Our brains process such information more thoroughly than good news. This might explain why we might focus on one criticism even though we also receive nine plaudits.

The surprise finding might be how social media might counter our Debbie downer tendency. The narrator highlighted studies that found how we might share and spread more positive content. Why?

We consume news as outside observers, but we use social media as active participants.

So actively sharing positive content might a coping and counter mechanism to how we are biologically wired.

But how we are wired keeps us vigilant. The point is not to shield ourselves or hide from bad news. That same news keeps us informed so that we can take action.

Video source

This episode introduced terminology at the heart of neural networks.

  • Architecture: Structure and connections of neurones.
  • Weights: Fine-tuning the computations.
  • Optimisation: Improving architecture and weights.
  • Loss function: Errors that AI makes in predictions.
  • Backpropagation: Providing feedback to weights to improve the computing process.
  • Local optimal solution: Best fit given limited conditions.
  • Global optimal solution: Best fit given better conditions.
  • Learning rate: How much the weights get adjusted during backpropagation.
  • Fitting to training data: Providing relevant information for meaningful output.
  • Overfitting: Allowing AI to find strong but meaningless correlations, e.g., between divorce rates and margarine consumption, or revenue from skiing and death by tangled bedsheets.

Correlation between divorce rates and margarine consumption.

Correlation between revenue from skiing and death by tangled bedsheets.

My guess is that human bias is strongly introduced with weights and training data. This could explain why current facial recognition has problems identifying people with dark skin.

Click to see all the nominees!

QR code

Get a mobile QR code app to figure out what this means!


Usage policy

%d bloggers like this: