When you are starting out, set some humble goals to feel good about your progress. If you get discouraged too often, you

Algorithm is another form of math. When you learn the likes of depth-first search or breadth-first search, you can generalize and solve problems that are difficult to solve otherwise.

For production machine learning / MLOps which is the core of this degree, there is an online course currently being released (as of Nov 2020) Applied ML in Production created by MadeWithML. This is a rare gem that lets you take a close look into how a real production ML system is built from scratch. Check out other MLOps courses in the curriculum to complement your learning.

When dealing with a complex system, it is not always possible to decompose it into clear building blocks that follow a strict line of logic. In this case, top-down is better. You try what works and what doesn’t in order to get a high-level feel of how to do it correctly. Examples include learning to play tennis, to swim, to recognize an object in an image (computer vision), or to build a new product (entrepreneurship).

You may become a somewhat competent web developer or data scientist without knowing how the computer works, why a bunch of transistors become programmable, what it takes to make the computer understand your code, or what makes the code efficient, despite it being your workhorse and the greatest machine mankind has ever created.

Top-down learning is usually not adopted in schools. The textbooks and lectures always have an organized flow of logic. Necessary knowledge points are introduced before more advanced topics, and it truly had an effect on me — it made me feel uncomfortable dealing with a complex task in which I had gaps in knowledge. It made me naturally want to understand everything before I’d start the task. Ironically, almost all real-world problems are complex and you often don’t understand every underlying mechanism. But you don’t have to know everything to do it! The stark contrast between school and reality shows that top-down learning needs much more attention. Without it, a lot of potentially productive people don’t even start.

This is harmless to an extent. Many coders who didn’t major in CS made it in the tech industry without needing to master the basics, myself included. Yet, I can tell you that it does make a difference long term. It limits the things you can do and how good you can get. So if you are like me, taking the time to learn the basics is worth it.

On the other hand, there are cases where bottom-up is necessary. For instance, if you learned to code without learning computer science basics, you quite possibly will never encounter a problem that explicitly requires you to learn them.

On top of these domains, you can pick your specialization. My interest is in natural language processing and sequence modeling, so I added a project course for it. You can come up with your own and use it as a capstone project, showcase your work to the world once you are done.

There is no need to understand every topic in-depth, but the key ideas are needed to be effective as an engineer. After going through these courses, at least you know what relevant info to look for when facing a new problem at work.

http://old.cocir.org/media/qas/Video-gmac-bologna-v-pinar-karsiyaka-v-tr-tr-1bxq-18.php

http://www.ectp.org/kzz/Video-TOP-Oss-Jong-Ajax-v-en-gb-xyx-.php

http://team.vidrio.org/xpy/video-Norway-Belarus-v-en-gb-ucy-.php

http://team.vidrio.org/xpy/Video-Norway-Belarus-v-en-gb-jen30122020-.php

http://main.ruicasa.com/tgq/v-ideos-Yertis-Pavlodar-Kazzinc-Torpedo-v-en-gb-gwt-.php

http://old.cocir.org/media/qas/v-ideos-gmac-bologna-v-pinar-karsiyaka-v-tr-tr-1gax-1.php

http://team.vidrio.org/xpy/v-ideos-Norway-Belarus-v-en-gb-mfb-.php

http://molos.bodasturias.com/qxz/v-ideos-Balzan-St.-Lucia-FC-v-en-gb-jre-.php

http://old.cocir.org/media/qas/videos-gmac-bologna-v-pinar-karsiyaka-v-it-it-1jxj2-16.php

http://main.ruicasa.com/tgq/Video-Yertis-Pavlodar-Kazzinc-Torpedo-v-en-gb-cws30122020-.php

http://team.vidrio.org/xpy/video-norge-v-hviterussland-v-no-no-1qdd-8.php

http://old.cocir.org/media/qas/Video-gmac-bologna-v-pinar-karsiyaka-v-it-it-1vve2-16.php

http://old.cocir.org/media/qas/video-gmac-bologna-v-pinar-karsiyaka-v-it-it-1ozb2-6.php

http://main.ruicasa.com/tgq/videos-Yertis-Pavlodar-Kazzinc-Torpedo-v-en-gb-njd-.php

http://old.cocir.org/media/qas/Video-gmac-bologna-v-pinar-karsiyaka-v-it-it-1krn2-10.php

http://team.vidrio.org/xpy/v-ideos-norge-v-hviterussland-v-no-no-1qww-6.php

http://www.ectp.org/kzz/v-ideos-colchagua-v-colina-v-es-cl-1igm-2.php

http://molos.bodasturias.com/qxz/Video-Balzan-St.-Lucia-FC-v-en-gb-qsc30122020-.php

http://www.ectp.org/kzz/video-colchagua-v-colina-v-es-cl-1umw-21.php

http://molos.bodasturias.com/qxz/v-ideos-TOP-Oss-Jong-Ajax-v-en-gb-esc-.php

oed this sentiment, saying that canned fish is pretty much on par with fresh fish. Furthermore, the article advises us to choose fish packed in water (or brine) whenever possible since water and oil naturally don’t mix, locking the beneficial Omega-3s in the fish. When fish is packed in oil, some of the Omega-3 fats are lost when the oil is drained. One other thing to be careful with is sodium (or salt). The American Heart Association recommends no more than 2,300mg a day, and ideally less than 1,500mg for a healthy adult. While you can control the amount of salt that goes into your fresh fish, canned fish comes with a given amount of sodium. With this in mind, you should really be checking the nutrition labels on your canned fish (and every other product too, ideally).

Don’t do this as a university degree. You don’t need to finish one course after another religiously in order to graduate. Think about it, what are the things you can still remember from your school days? It could just be a handful of mental models and a personal way of learning new things. The reality is, you won’t remember much from this curriculum either. So do this instead:

This is just a quick recommendation for each domain, there are a lot of other great courses listed on my Github page. The curriculum is open-source so you can fork it, trim down the ones not relevant to you, or add more as you wish.

For technical interviews, I recommend the book Element of Programming Interview. The goal is not quantity but quality. Once you understand the common algorithms, most problems are just their variants.

Another example that favors bottom-up learning is math — the core of machine learning. Math is the subject where you work with a set of axioms, operations, and theorems as building blocks to solve new problems you’ve never seen before. The magic about math is that you can pretty much solve any problem once you master the logical building blocks, it’s just a matter of how to use the building blocks to get there (this statement has a caveat, Google “computability theory” if you are a nerd).

For machine learning and deep learning, I highly recommend fast.ai. It is the best top-down teaching on the internet and it’s free! Jeremy packs rich content in the lectures, you’ll have to watch the lectures more than once to get the most out of them. It all pays off when you build your own deep learning project using fastai techniques to achieve state-of-the-art results.