A note from 2048

It may not seem like it now but those extra hours you put into building your skills all added up.

Taking care of your health was also the right thing to do.

And don’t forget to keep reminding those close to you how much you love them.

Keep learning, keep moving, keep loving.

Best,

Your 2048 self.


PS the latest episode of Learning Intelligence is out, I’ve been learning all bout the Google Cloud Platform. I’m still a novice when it comes to dev ops but it’s becoming more and more a requirement in my day to day work. So I figured I better start getting on top of it. And make my 2048 self proud.


What to do when you can't get the right answer

If you’ve been stuck on a problem for a while and it’s not leading anywhere, reframe the question.

It’s easy to get stuck in one way of thinking.

All you need is three words.

Read, try, ask.

Read what you can about it.

Try to implement what you’ve read.

And if your eyes can’t see the answer, someone else’s ears may be able to hear the right question. Ask them. Speaking out loud may help you realise what you’re actually trying to do.

We were made to work together.

Read.

Try.

Ask.

And again.

Eventually, you’ll be the person people come and ask. Make sure they’re asking the right question.

Four hours per day

Is all you need.

If you want to learn something, the best way to do it is bit by bit.

Cramming for exams in university never worked for me. I remember walking into campus straight to the canteen on exam day.

‘Two Red Bulls please.’

Then my knee would spend the next two-hours in the exam room tapping away but my brain would fail to connect the dots.

The most valuable thing I took away from university was learning how to learn.

By my final year, my marks started to improve. Instead of cramming a couple of days before the exam, I spread my workload out over the semester. Nothing revolutionary by any means. But it was to me.

Now whenever I want to learn something, I do the same. I try do a little per day.

For data science and programming, my brain maxes out at around four hours. After that, the work starts following the law of diminishing returns.

I use the Pomodoro technique.

On big days I’ll aim for 10.

Other days I’ll aim for 8.

It’s simple. You set a timer for 25-minutes and do nothing but the single task you set yourself at the beginning of the day for that 25-minutes. And you repeat the process for however many times you want.

Let’s say you did it 10-times, your day might look like:

8:00 am

Pomodoro 1

5-minute break

Pomodoro 2

5-minute break

Pomodoro 3

5-minute break

Pomodoro 4

30-minute break

10:25 am

Pomodoro 5

5-minute break

Pomodoro 6

5-minute break

Pomodoro 7

5-minute break

Pomodoro 8

60-minute break

1:20 pm

Pomodoro 9

5-minute break

Pomodoro 10

5-minute break

2:20 pm

Now it’s not even 2:30 pm and if you’ve done it right, you’ve got some incredible work done.

You can use the rest of the afternoon to catch up on those things you need to catch up on.

Don’t think 10 lots of 25-minutes (just over 4-hours) is enough time to do what you need?

Try it. You’ll be surprised what you can accomplish in 4-hours of focused work.

The schedule above is similar to how I spent my day the other day. Except I threw in a bit of longer break during the middle of the day to go to training and have a nap.

I was working through the Applied Data Science Specialization with Python by the University of Michigan on Coursera. The lessons and projects have been incredibly close to what I’ve been doing day-to-day as a Machine Learning Engineer at Max Kelsen.

PS best to put your phone out of sight when you’ve got your timer going. I use a Mac App called Be Focused, it’s simple and does exactly the above.

I got high with a stranger in a Japanese hostel lobby - here's what I learned

We were talking on the couch in a hostel lobby in Tokyo. It was snowing outside, the first time in November for 60-years.

My friend had gone to sleep, he had a flight to catch the next morning.

The guy I was talking to was from America.

He had just finished telling me how he brought his vape (electronic cigarette) into Japan. He had a medical permit to smoke cannabis back home.

"Cannabis is highly illegal in Japan, up to a 10-year jail sentence," he told me.

“The Japanese customs have never seen this.” he pulled out a few vials of hashish oil.

I was writing in my journal what I had been up to that day as I was talking to this guy. He had some cool stories and I didn’t want to be rude so I turned off my iPad.

“Want to try some?” he asked.

I didn’t respond he just handed me the vape.

“You just push the button on the top and suck it in.”

“Alright,” I said.

I could hear the liquid bubbling as I held the button down. I had no idea what hashish oil was but I’d heard it was some kind of cannabis plant extract.

THHHHHHHHHHLLLLLLP.

I inhaled the vapor.

My eyes dilated immediately. Like the feeling, you get when you look at yourself half asleep in the mirror and try to stretch your face out.

“Take another.” he said.

One was more than enough.

THHHHHLPPPPPPP.

Again.

My whole body relaxed. It was like a dozen masseurs had decided to treat me for the evening, all at the same time.

Whatever I was writing was now definitely on pause.

I noticed myself starting to struggle to tie thoughts into a sentence. The words were there in my head but I couldn’t say them to the guy I was talking to.

I laid down on the couch.

“Maybe two was a bit much, my bad, enjoy it dude.”

Time dissolved. Everything was happening at the speed of light and at a stand still at the same time.

I started feeling as if the couch was pushing up against me rather than gravity pulling me down.

The guy was telling me stories about his life back in the US.

“Okay.” was all I could reply.

He had way more hits than me so maybe he was feeling the same. His tolerance was probably way higher.

I turned my head to try look behind the couch. When I moved my body I could feel again. I started shaking my head, with every change in direction I’d get some sense of the world but when I stopped, everything went back to being nonsensical.

“I’m going out to smoke a cigarette. Want to join?” he asked.

“No thank you.” I think I replied.

When he left I tried to get back to writing. I wanted to document my current situation.

As I sat up the demons started creeping in. What I’d done just hit me. I’d just smoked a variant of cannabis in Japan. I could go to jail if they found me.

I needed a way to sober up so I started to text my friends, they had a bit more experience than I did.

 An example of what I was sending my friends. There's two more pages.

An example of what I was sending my friends. There's two more pages.

The paranoia started to kick in. I thought the guy was going to try and rob me.

Step 1: Get me high.

Step 2: Take my stuff.

I thought it was such a genius plan.

I decided I better take myself back to my room.

Everything was in slow motion. Seriously slow motion. My room was no more than 20 meters from the lobby.

By the time I put my stuff together in a pile and got myself off the couch, it took me 40-minutes to get back.

My bed was the bottom half of a bunk bed. I was sharing a dorm room with 12 or so other guests. I wondered if they knew how high I was.

I put my stuff in my bag and put my bag next to my pillow. I was travelling with one bag.

Because the rooms had so many people, the bunks had black out curtains so you’d at least get a little privacy.

I managed to close my curtains.

Then it began.

My sheets were white and the curtains completely black. As I laid down, it felt like I was floating through space. The blackness of the curtains was a perfect backdrop for the emptiness of space.

I was on a magic flying bed on a journey through the boundless universe.

The guy above me was doing some kind of update on his Windows laptop which was less than ideal theme music for my adventure but I didn’t have many options.

As I hovered through space with no sense for time, I managed to drift off to sleep. I slept for 14-hours. I woke up 30-minutes past the time I was supposed to check out from the hostel.

The guy who gave me the vape was in the bunk across from me, he had already checked out.

My bag was still next to my head untouched.

I was afraid for no reason.

I packed up my gear, got a photo with my friend on the hostel guest board. And went outside to check out the snow, the first time in 60-years. And the second time I’d ever seen snow. What a day.

Moral of the story?

Get super high in a hostel lobby with a stranger you’ve never met and realise most of our fears are in our mind and not in reality.

Source: http://qr.ae/TUpql6

How I'm Learning Deep Learning - Part IV

Is a wealth of data the final frontier?

 

This article is part of the How I’m Learning Deep Learning Series on Medium:

Part I: A new beginning.
Part II: Learning Python on the fly.
Part III: Too much breadth, not enough depth.
Part IV: AI(ntuition) versus AI(ntelligence). (You’re currently reading this)
Extra: My Self-Created AI Master’s Degree

 A few of the resources helping me break into the world of AI. — Hinton Image  Source

A few of the resources helping me break into the world of AI. — Hinton Image Source

A lot has happened since Part III. While the last couple of articles went in-depth into what exactly I was learning, this one will be a little different. Rather than break it down week by week, I’ll cover the major milestones.

I graduated from the Udacity Deep Learning Nanodegree (DLND) in August last year. Thinking about how I emailed the support team asking what the refund policy was before starting the course makes me laugh. It was easily one of the best learning programs I’ve ever taken. If you’re after more details, I recently published an in-depth review video on the DLND.

Making videos about my journey has led to some great conversations with others on the same path. I met someone in Canada who was doing almost the exact same courses as me. Even more interesting is that we have the same poster of Arnold in our room. Small world.

More recently, I had the opportunity to have a conversation with Shaik Asad, a 14-year-old AI developer from India. He teaches himself AI after completing his homework. Since then we’ve been actively chatting about life and our other interests. Seeing how passionate Shaik is about AI and hearing what his goals are, inspired is an understatement.

AI Master’s Degree

After graduating from the DLND, I was a deer in the headlights. I’d learned all about the amazing power of deep learning (DL) but still didn’t fully understand what really made deep neural nets tick. I was also left wondering whether DL is the be all and end all of Artificial Intelligence (more on this later).

I needed to know more. Curiosity led me to create my own AI Master’s Degree. Having a rough outline of a curriculum to follow allowed me to narrow down how I would spend my time. My mission is to use AI to help people move more and eat better. I have skin in the game in the world of fitness and nutrition, I’m working on the AI side.

In the past few months, I’ve completed 80% of the Coursera Deep Learning specialisation (course 5 was just released as of writing) by Andrew Ng and the team at deeplearning.ai as well as Term 1 of the Udacity Artificial Intelligence Nanodegree (AIND).

For those who learn from a ground-up approach, the deeplearning.ai specialisation is the best place to start learning about DL. If you’re more into diving into project building, or want to progress with one of Udacity’s advanced Nanodegrees, start with the DLND.

Term 1 of the AIND covered classical AI approaches. It lost me at times due to my lack of programming ability and my recent focus on DL. However, learning about how far the field has come since inception was fascinating.

I’m into Term 2 now, which includes building projects in computer vision, natural language processing and speech recognition using DL. Back in a familiar fishbowl.

I’ll release a full in-depth review of the deeplearning.ai and AIND once I’ve completed them both.

Future of AI

After learning more about how DL works, I started to become suspicious of what its longevity prospects are. Many DL models need a ridiculous amount of data to produce a useful output.

This is well and good if you’re one of the two companies in the world with enough data to keep Titanic afloat but not so good if you’re a young AI hopeful. Deep Learning has brought about many incredible insights but many of which are in the realm of supervised learning, which still takes a lot of human input.

Although our ability to gather and produce data is increasing exponentially, I’m not convinced more data is the key to solving all of our AI problems.

Are we really just data-processing machines? Last century, people thought our internal processes could be modelled using the concept of steam engines. The man with a hammer problem comes to mind.

Back-propagation (an algorithm to help neural networks improve themselves) does not work very well on unlabelled data, which is what most of the universe is comprised of.

Consider a four-year-old walking into a room they’ve never been in. The young child doesn’t require 10,000 labelled images of a room to know how to navigate it. They don’t even require one labelled image of a room, they simply start interacting with it.

Even the godfather of Deep Learning seems to be thinking along the same lines. In an interview late last year, Geoffrey Hinton was asked his opinion on the current state of AI techniques.

“My view is throw it all away and start again.” 
 
 “The future depends on some graduate student who is deeply suspicious of everything I have said.”

Listening to the lectures and talks of Monica Anderson (especially the one on dual-process theory) and discovering her work on Artificial Intuition as an approach to Artificial Intelligence raises more questions on the matter.

I will delve deeper into these topics in a future post.

Next Steps

Over the next few months, I will be completing the curriculum I have set out for myself.

I just submitted the first major project of Term 2 of the AIND, a computer vision model to detect facial keypoints.

For each of the upcoming major projects, I will be posting an article detailing my understanding of the work as well as a step-by-step guide for those looking to build an equivalent.

I’m also thoroughly enjoying the free courses on offer from MIT on Artificial General Intelligence and Deep-Learning for Self-Driving Cars.

After completing the AIND, fast.ai seems likely to be my next port of call.

By the time I finish up my curriculum, I will be looking to move to the US to join a startup in the world of health and AI (or create my own). If you know anyone or think I should be following anyone currently playing at the crossroads of health and AI, please let me know.

For those considering embarking on their own self-led learning journey or finding out more about AI, the words of Naval Ravikant sum it up perfectly.

The current education system is a path depended outcome. We have the internet now, if you actually have a desire to learn, everything is on the internet. The ability, means and tools to learn are abundant and infinite, it’s the desire to learn that’s incredibly scarce.

See you in Part V.

Source: https://hackernoon.com/how-im-learning-dee...