Here, you’ll discover the latest posts that explore new insights, creative projects, and unique perspectives on the world. Dive in, explore, and uncover something new with every read.
디퓨전 없이도 생성이 가능할까? Drifting Model은 왜 “학습과정 자체”를 생성 경로로 바꾸려 했을까 생성 모델을 처음 배울 때 가장 자연스럽게 떠오르는 그림은 이렇다. 노이즈에서 시작해서, 여러 번의 정제를 거쳐, 조금씩 데이터 분포에 가까워지는 과정. 디퓨전도 그렇고, 플로우 매칭도 그렇다. 결국 추론 과정에서 여러 단계의 변환을 거쳐 복잡한 pushforward를 만들어내는 방식이다. 그런데 이 논문은 질문을 조금 다르...
“Classifier-Free Diffusion Guidance”는 조건부 생성(conditional generation) Diffusion Model을 개선한 논문입니다. 이 논문이 발표되기 이전, 특정 클래스의 이미지를 생성하도록 모델을 유도하는 일반적인 방법은 별도의 이미지 분류기(Classifier)를 활용하는 ‘Classifier Guidance’였습니다. 이 방식은 효과적이었으나, Diffusion Model 외에 노이즈 낀 이...
2020년 발표된 “Denoising Diffusion Probabilistic Models” (DDPM)은 생성 모델 연구에 중요한 전환점을 제시한 논문입니다. 당시 Generative Adversarial Networks (GANs)는 훈련 불안정성과 모드 붕괴(mode collapse)와 같은 문제점에도 불구하고 높은 성능으로 인해 고품질 이미지 생성 분야에서 널리 사용되고 있었습니다. DDPM은 이러한 상황 속에서 Diffusion...
The Z-transform is a powerful mathematical tool that extends the Fourier Transform to analyze discrete-time signals and systems. This article covers its fundamental concepts, including stability analysis, poles and zeros, and its role in solving difference equations.
This post introduces the Discrete Fourier Transform (DFT) for frequency analysis and the Fast Fourier Transform (FFT), which optimizes computation using a divide-and-conquer approach.
This article explores the process of converting continuous analog signals into digital form, detailing each step—from pre-processing and A/D conversion to D/A reconstruction using methods like ideal, zero-order, and first-order holds. It also discusses key challenges such as aliasing and practical limitations in achieving perfect signal recovery.
This article introduces the key concepts of LTI systems using impulse response, convolution, and difference equations. It explains how these concepts reveal the system's behavior and how to mathematically solve for its response.
This article explores the basics of discrete-time signals, including periodic signals and key types like impulse, step, and exponential signals. It also explains LTI systems and how to analyze their stability.
This article will explore the fundamental concepts that arise in Digital Signal Processing (DSP). It will cover concepts such as signals and systems, sinusoids, energy, and power. Examples will be provided to reinforce understanding.
Discover how the Discrete Time Fourier Transform (DTFT) connects discrete signals to their frequency domain representation. By exploring its mathematical foundations, you'll understand its crucial role in digital signal processing.
This article simplifies the concept of Fourier Transform for those without prior exposure to signals and systems. It covers Fourier Series, Continuous Time Fourier Transform (CTFT), and its inverse with step-by-step explanations.
Discover how linear transformations are represented in different bases and why similar matrices preserve essential properties. Understand the mathematics behind change-of-basis operations.
Explains the principles and characteristics of L1 and L2 regularization, their connection to Maximum a Posteriori (MAP) estimation, and how to apply regularization to prevent overfitting in deep learning models.
Explore the concept of linear transformations from basics to matrix representation and inverse transformations, providing an intuitive understanding of vector space mappings.
Explore the concepts of two-way and multi-way ANOVA, delving into interactions between factors. Conclude with a comprehensive summary of ANOVA techniques.
Discover the fundamentals of Analysis of Variance (ANOVA) and dive into one-way ANOVA to analyze differences between group means.
A statistical method used to evaluate whether differences between two sample means are significant or due to chance.
A detailed exploration of Cross-Entropy and KL Divergence, deriving their formulas step-by-step from the principles of probability and information theory.
