신경식의 딥러닝 - Gradients and PyTorch's Autograd
공대형아(신경식)
딥러닝을 시작하기 위해 필요한 기본적인 미분법과 PyTorch의 Autograd 기능을 배우는 강의입니다.
초급
딥러닝, 미적분, PyTorch
This is a lecture on how to use NumPy and practice its application in real-world scenarios.
NumPy
Data processing
Data operation
This lecture is part of the pre-semester (preparatory semester before this semester) of the artificial intelligence specialized curriculum All about AI.
Data processing libraries: NumPy, Matplotlib, Pandas
This lecture covers the most core NumPy .
Miro Link: https://miro.com/app/board/uXjVNJ8PZSs=/?share_link_id=801072444784
For an introduction to All About AI, please refer to the orientation lecture.
NumPy is an abbreviation for Numerical Python and is a library specialized in operating on vectors, matrices, and higher-order tensors .
This NumPy is an essential technology for anyone who handles data using Python, and because it is the most universally used, it is a library that will serve you well once you learn it .
In the future, we will be implementing machine learning and deep learning algorithms directly using NumPy, so this is a library that you must learn properly before learning them in earnest.
NumPy is quite compatible with other libraries that deal with data.
Therefore, once you learn NumPy properly , you can lower the barrier to entry when using other libraries.
Most lectures or textbooks that cover NumPy
np.sum, np.hstack, np.histogram
We focus only on how to use APIs such as .
But! What is definitely more important when using NumPy is
Broadcasting, Fancy Indexing, Vectorization
This is to create fast code using the ndarray object provided by NumPy.
Therefore, in this lecture, we will cover not only the essential APIs provided by NumPy, but also a considerable number of fundamental techniques that can help you use NumPy more efficiently .
This will make you one of the most fundamentally sound people when it comes to writing code to process data.
In this lecture, you will learn how to use the essential APIs provided by NumPy, as follows:
np.array
np.zeros
np.ones
np.empty
np.full
np.zeros_like
np.ones_like
np.empty_like
np.full_like
np.arange
np.linspace
np.positive
np.negative
np.add
np.subtract
np.multiply
np.power
np.divide
np.floor_divide
np.remainder
np.equal
np.not_equal
np.greater
np.greater_equal
np.less
np.less_equal
np.logical_not
np.logical_and
np.logical_or
np.logical_xor
np. all
np. any
np.isclose
np.allclose
np.square
np.reciprocal
np.sqrt
np.cbrt
np.exp
np.exp2
np.expm1
np.log
np.log2
np.log10
np.log1p
np.deg2rad
np.radians
np.rad2deg
np.degrees
np. sin
np. cos
np. tan
np. sinh
np. cosh
np. tanh
np.sign
np.absolute
np.trunc
np. floor
np. ceil
np.round
ndarray.round
np.clip
ndarray.clip
ndarray.copy
ndarray.view
ndarray.flatten
ndarray.flat
numpy.ravel
ndarray.ravel
np.reshape
ndarray.reshape
np.resize
ndarray.resize
np.squeeze
ndarray.squeeze
np.expand_dims
np.newaxis
np.moveaxis
np.swapaxes
np.transpose
ndarray.transpose
np.arcsin
np.arccos
np.arctan
np.sinh
np.cosh
np.tanh
np.sign
np. abs
np.floor
np.ceil
np.clip
np. round
np.trunc
np.fix
np.random.rand
np.random.random
np.random.uniform
np.random.randint
np.random.randn
np.random.normal
np.random.choice
np.random.permutation
np.random.shuffle
np.random.seed
np.random.default_rng
rng.random
rng.uniform
rng.integers
rng.standard_normal
rng.normal
rng.permutation
rng.choice
rng.shuffle
np. sum
ndarray.sum
np.prod
ndarray.prod
np.mean
ndarray.mean
np.var
ndarray.var
np.std
ndarray.std
np.max
ndarray.max
np.min
ndarray.min
np.median
np.percentile
np.maximum
np.minimum
np.memdian
np.histogram
np.cumsum
ndarray.cumsum
np.cumprod
ndarray.cumprod
np.ptp
ndarray.ptp
np.diff
np.sort
ndarray.sort
np.argsort
ndarray.argsort
np.argmax
ndarray.argmax
np.argmin
ndarray.argmin
np.nonzero
ndarray.nonzero
np.where
np.unique
np.hstack
np.vstack
np.concatenate
np.append
np.hsplit
np.vsplit
np.split
np.partition
ndarray.partition
np.argpartition
ndarray.argpartition
np.repeat
ndarray.repeat
np.tile
np.meshgrid
np.linalg.norm
np.dot
ndarray.dot
np.cross
np.outer
np.identity
np.eye
np.diag
np.trace
ndarray.trace
ndarray.transpose
ndarray.T
np.matmul
np.linalg.det
np.linalg.inv
np.linalg.eig
ndarray.dtype
np.intX
np.uintX
np.floatX
ndarray.itemsize
ndarray.nbytes
ndarray.astype
np.save
np.load
np.savez
np.savez_compressed
And in the following chapters, you will learn the fundamental usage of ndarray .
Chapter.5 - Broadcasting
Chapter.7 - Integer Indexing
Chapter.8 - Boolean Indexing
Chapter.9 - Slicing on ndarrays
Chapter.20 - Vectorization Techniques
In this lecture, we will review NumPy's API, ndarray technologies, and write code that is actually used in machine learning and deep learning.
In the future, we will implement various algorithms based on what we learned in this lecture.
I hope this will be an opportunity to solidify my knowledge of NumPy in order to create interesting algorithms in the future.
Who is this course right for?
For those who want to learn NumPy properly.
Someone who does data analysis
People who are learning machine learning and deep learning
Need to know before starting?
Basic Python Syntax
2,947
Learners
117
Reviews
81
Answers
5.0
Rating
13
Courses
[멋쟁이 사자처럼] 인공지능중고급과정
[국립기상과학원] 2022년, 2023년, 2025년 기상 AI 부스트캠프
[삼성전기] 신입SW과정 전문반
[국가과학기술인력개발원] R&D 수행 역량 강화 장기 멘토링
[국가과학기술인력개발원] R&D 전문과정 이러닝 컨텐츠 제작
[국가과학기술인력개발원] 박사후연구원 연구 데이터 시각화 과정
[원광대학교] 원광대학교 AI 집체교육 및 AI 장단기과정
[한국지능정보사회진흥원] SW여성인재 교육
[SK m&service] 데이터 기반 의사결정
[한국IT비즈니스진흥협회] ICT COG Academy
[서울시 교육청] 신기술분야 연수
[KT] KT AI 역량향상 과정
[K-ICT] 데이터 안심구역 분석캠프
[경기도경제과학진흥원] 처음으로 배우는 비전 AI
[경기도경제과학진흥원] 파이썬 데이터 분석 입문
[서울과학기술원] AI 활용 심화교육
[서울대학교] AI 활용 역량강화 교육
[HD한국조선해양] AIC AI 연구직 역량 평가 개발
[멀티캠퍼스] 원리부터 구현까지, 머신러닝 핵심 알고리즘 마스터
[패스트캠퍼스] 수학적으로 접근하는 딥러닝
[패스트캠퍼스] 한 번에 끝내는 머신러닝과 데이터분석 A-Z
[패스트캠퍼스] 바이트 디그리 Lv.2 Deep Learning Essentials
[패스트캠퍼스] 딥러닝인공지능 초격차
[패스트캠퍼스] 컴퓨터 공학 초격차 VER.2
All
192 lectures ∙ (35hr 9min)
Course Materials:
All
4 reviews
5.0
4 reviews
Reviews 9
∙
Average Rating 4.1
5
파이토치를 배우기 위한 밑거름 강의... 최고입니다. 신경식 강사님의 강의는 언제나 옳다 !!!
감사합니다!! 더 좋은 컨텐츠의 강의 제공할 수 있도록 최선을 다하겠습니다😃
Reviews 2
∙
Average Rating 5.0
Reviews 13
∙
Average Rating 5.0
Reviews 2
∙
Average Rating 5.0
$35.20
Check out other courses by the instructor!
Explore other courses in the same field!