Live coding 16

[Daniel (深度碎片)]

@Moody

Jeremy used Excel to explain softmax (maths), cross-entropy (maths), gradient descent with different variations (maths and solver add-on), convolution (visualisation), and recommendation system (matrix multiply and solver add-on)

To reproduce this list in excel step by step should be a great exercise for me!

@Moody

While I was running (and waiting impatiently) Part 2 notebooks, I kept using Excel to understand/experiment with the following concepts:

• Gradient explosion for CycleGAN
• Wasserstein GAN (comparing L1 and L2 losses)
• Artifact when up-sampling images using different methods and kernel sizes

If you are interested, here is the repo. Feedback is welcome.

Wow, this is very nice! More advanced and challenging exercise!

@Moody

Knowing the impacts and reasons for picking certain parameters/loss functions are far more important.

Very true! It’s one thing to try the newly implemented techniques and say it works better by lower error rate, it’s another to ‘see’ how the new techniques behave differently and how the difference may contribute to better result.

@Moody

data collection registration (since we needed to collect our own ground truth dataset)

This sounds very interesting! Love to learn more of how to build a dataset professionally using Excel from you someday.

@Moody

mock up model specifications (breaking down into input, process, and output) to avoid misunderstanding and using the predefined output for User Acceptance Test later. (Very important for system customisation projects to ensure projects are delivered on time and on budgets)

So, you have actually implemented in Excel every step of your deep learning project from input to model building to output? Wow! That’s amazing! Love to learn more of the story of how you did it!

@Moody

I successfully applied the above with a multi-disciplines team, located in four different time zones, to deliver a deep learning project - using computer vision for digital pathology. Last year, my team published the finding in Nature’s Scientific Report.

Congratulations! This is huge!

@Moody

if Jeremy did not use Excel in his teaching, I would not contemplate learning deep learning at all. Without fastai, I might possibly still use Excel and work in Finance/Accounting. But now, fastai opens up a whole new world for me to explore.

Yeah, Jeremy definitely should teach us his tips in using Excel particularly for deep learning. I guess we should give Jeremy more positive feedbacks on Excel with deep learning.