post_01-learn_pt_tf In [20]: from IPython.display import HTML, display, Math import warnings warnings.filterwarnings('ignore') Learn pyTorch and Tensorflow Simultaneously¶ If you are interested in machine learning and can’t decide whether to learn pyTorch or Tensorflow, this is an article for you. Why should we fall for the hassel of learning one then migrating to another, when we can possibly learn both at once? From version 2.0, Tensorflow’s coding experience started to be much similar to pyTorch—thanks to the introduction of Gradient tape. Following this series of tutorials, you can quickly become profecient in both pyTorch and Tensorflow. Tape-based Graient Computation¶ “Wengert list” [1] …
Author: itanveer
Human Readable Git Log (Copied)
This post is shamelessly copied from https://coderwall.com/p/euwpig/a-better-git-log in order to keep it as a future reference. I guess that’s a bit too long, eh? Let’s just make an alias. Copy and paste the line below on your terminal: And every time you need to see your log, just type in Or, if you want to see the lines that changed
Current HCI Design Pipeline
I think the current Human-Computer Interaction field, even though works practically, but uses an unsmart procedure. Involving human evaluation at every stage of interaction design is a brute force solution. A better solution is likely to exist. Understanding the human behaviors and finding human responses to various stimuli is the first step in designing better interaction design. By the way, understanding human behavior not only helps HCI, it helps human-human interaction as well.
5 Interesting Facts of Matrix Calculus
Matrix calculus is the extension of calculus to vector or matrix setting. I used to suffer a lot with matrix calculus in my early grad life. I’ve seen some other people to suffer as well. It primarily happens because the standard courses in linear algebra do not cover this topic very often. However, all the maths in Matrix calculus are basically trivial. Anyway, here are a few interesting facts that made my life much easier. I could use these to derive many expressions (e.g. calculating gradients in SGD based algorithms etc.) in my machine learning practice. Check if they can help you or not. …
Definition of “Usually”
It is a pain to talk with people suffering from superiority complex. The hard work that is vital for acquiring knowledge often brings a delusion of grandeur to some people. They often think that only they can talk in perfect English. Everyone else’s English is just imprecise and bogus. Many of them also show a demeaning attitude. Whenever you’ll say something, they’ll try to point out how your sentence construction is syntactically wrong or mathematically imprecise. Once I met such a delusional person who had some kind of enmity with the word “usually”. I must concede that I, sometimes, use this word a little too …
No Rule other than Just Not Hurting Others?
Recently, I was engaged in a long argument in Facebook on what should be the extent of laws in a country. I was defending an argument similar to the one written in the title. I think I came up with some really interesting logic against the proposition. I’m preserving these here. As it was a part of an ongoing conversation, it might sound awkward. The full conversation is available in this Facebook post. Check out the replies of the second comment.
Teaching Style: Where Many Computer Scientists and Mathematicians Do it Wrong
There is a difference between programming and teaching. I have seen a lot of good programmers to be a horrible teacher. In my opinion, this happens when people become delusional in thinking that teaching is just like writing programs — tell each and every step, in a logically perfect sequence. In reality, teaching is more than that. First of all, humans don’t need everything to be spelled out. In fact, that is detrimental to teaching (I’ll explain why later). Humans just need broad thick strokes here and there. They are good in connecting the strokes and building perfect picture themselves. In my opinion, the most important objective of teaching …
Digital age or Dark age?
When people used to work with pen and paper, their knowledge used to become a part of the physical world. Once they were deceased, human could still partially access to their thoughts by accessing the papers they scribbled on. Many unpublished articles, personal letters, even drawing and scribbles became part of our history in this way. What is the condition now for digital age? All the writings we are making in the digital form, how will they survive? What will happen if a great scholar dies and no one knows the password of that scholar’s laptop? Or, what if the …
Instill Pain Endurance?
Should I try to stay in a first world country or should I try to go back to Bangladesh? It is a really difficult question to answer. I’ve been thinking on this sporadically over the last 6 years. There are a lot of selfish reasons for staying in USA, a lot of noble reasons for going back to Bangladesh. But I wanted to find a few solid selfish reasons for going back to Bangladesh. I’ve just found one –> To Instill pain endurance; both for me and my family. Pain endurance is a source of happiness. But to endure pain, one has to …
ডীপ লারনিং- কৃত্রিম বুদ্ধিমত্তার আধুনিকতম উপহার
যারা কম্পিউটার বিজ্ঞানের নিত্য নতুন আবিষ্কার সম্পর্কে ধারণা রাখেন তারা সবাই কৃত্রিম বুদ্ধিমত্তা বা Artificial Intelligence সম্পর্কে জানেন। এমনকি যারা কম্পিউটার বিজ্ঞান সম্পর্কে কোনও ধারণাই রাখেননা তাদেরও অনেকেই সায়েন্সফিকশন মুভির কল্যাণে এটা সম্পর্কে জানেন। এই কৃত্রিম বুদ্ধিমত্তা বিষয়টার একটা অংশ হল মেশিন লার্নিং (বাংলায় কি আমরা একে “যান্ত্রিক শিক্ষা” বলতে পারি? কিন্তু আমার কাছে মেশিনলার্নিং টাই ভালো শোনায়)। মেশিন লার্নিং ফিল্ডটা নিয়ে যারা নাড়াচাড়া করেন তাঁদের মাথা ঘামানোর প্রধান বিষয়বস্তু হোল এমন একটা কম্পিউটার প্রোগ্রাম বানানো যা কিনা নিজে নিজেই কোন কিছু শিখে নিতে পারে। এই মেশিন লার্নিং ফিল্ডে ইদানীং একটা বড় (আবিষ্কারের) বিপ্লব ঘটে চলেছে। একে বলা হচ্ছে ডীপ …