JaKeoung Koo jakeoung

약자	한국정보과학회 (2024)	BK21플러스 IF (2018)	KAIST CS (2022)	SNU CSE (2024.4)	POSTECH CSE (2024.9)	평균 (정규화)	학회명	DBLP Key
AAAI	최우수	4	O	O	최우수	1.00	AAAI Conference on Artificial Intelligence (AAAI)	conf/aaai
AAMAS	우수	2				0.20	International Conference on Autonomous Agents and Multiagent Systems (AAMAS)	conf/ifaamas
ACCV	우수	1			우수	0.25	Asian Conference on Computer Vision (ACCV)	conf/accv
ACL	최우수	4	O	O	최우수	1.00	Annual Meeting of the Association for Computational Linguistics (ACL)	conf/acl
ACL Findings	우수				우수	0.20	Findings of ACL	series/findacl
ACNS	우수					0.10	International Conference on Applied Cryptography and Network Security (ACNS)	conf/acns
ACSAC	우수	2			우수	0.30	Annual Computer Security Applications Conference (ACSAC)	conf/acsac
AIED					우수	0.10	International Conference on Artificial Intelligence in Education (AIED)	conf/aied
AISTATS	우수	1			우수	0.25	International Conference on Artificial Intelligence and Statistics (AISTATS)	conf/aistats

In this video we come across about 50 online resources for category theory:

https://youtu.be/hEW42ARKNoE

I quickly comment on about 20 major ones. I link to the university sites, arXiv sites or Amazon page - most of the mentioned books are online available.

Here's another category theory list on github

https://github.com/prathyvsh/category-theory-resources

Semantic Commit Messages

See how a minor change to your commit message style can make you a better programmer.

Format: <type>(<scope>): <subject>

<scope> is optional

Example

A Tour of PyTorch Internals (Part I)

The fundamental unit in PyTorch is the Tensor. This post will serve as an overview for how we implement Tensors in PyTorch, such that the user can interact with it from the Python shell. In particular, we want to answer four main questions:

How does PyTorch extend the Python interpreter to define a Tensor type that can be manipulated from Python code?
How does PyTorch wrap the C libraries that actually define the Tensor's properties and methods?
How does PyTorch cwrap work to generate code for Tensor methods?
How does PyTorch's build system take all of these components to compile and generate a workable application?

Extending the Python Interpreter

PyTorch defines a new package torch. In this post we will consider the ._C module. This module is known as an "extension module" - a Python module written in C. Such modules allow us to define new built-in object types (e.g. the Tensor) and to call C/C++ functions.

	# We can produce samples from an un-normalized distribution by adding
	# iid Gumbel noise together with the argmax operator; which is denoted as the Gumbel-Max Trick.
	# However, argmax doesn't produce meaningful gradient signals, so we replace argmax
	# by softmax, with a temperature parameter (Gumbel-Softmax Trick).
	#
	# I didn't invent any of this, all credit goes to the following papers:
	# - https://arxiv.org/abs/1611.00712
	# - https://arxiv.org/abs/1611.01144

	import numpy as np

	'''
	This file is heavily inspired by https://github.com/j-towns/ans-notes/blob/master/rans.py

	We describe a variant of bits-back coding called BB-Huffman. This file is meant
	purely as an educational tool and is in no way optimized. The goals are to

	1. illustrate how bits-back coding can be used with Huffman-like codecs;
	2. and how the cost of using a selector to toggle between codebooks can be greatly reduced.

	- Symbols are integers between 0 and 2;

	import math
	import torch
	import torch.nn as nn
	import torch.nn.functional as F
	from torch.nn.modules.utils import _pair, _quadruple


	class MedianPool2d(nn.Module):
	""" Median pool (usable as median filter when stride=1) module.

	from graphviz import Digraph
	import torch
	from torch.autograd import Variable, Function

	def iter_graph(root, callback):
	queue = [root]
	seen = set()
	while queue:
	fn = queue.pop()
	if fn in seen:

	#reference https://unix.stackexchange.com/questions/136371/how-to-download-a-folder-from-google-drive-using-terminal
	#get cookie and code
	wget --save-cookies cookies.txt --keep-session-cookies --no-check-certificate 'https://docs.google.com/uc?export=download&id=FILEID' -O- \| sed -rn 's/.confirm=([0-9A-Za-z_]+)./Code: \1\n/p'

	#download the file
	wget --load-cookies cookies.txt 'https://docs.google.com/uc?export=download&confirm=CODE_FROM_ABOVE&id=FILEID'

	Pretty print tables summarizing properties of tensor arrays in numpy, pytorch, jax, etc.

	Now on pip! `pip install arrgh` https://github.com/nmwsharp/arrgh