- 전체보기(16)
- Representation Learning(2)
- Deep Learning(2)
- meta learning(2)
- MAML(2)
- MDP(1)
- review(1)
- Few-shot Learning(1)
- Knowledge Graph(1)
- SegFormer(1)
- Tensor(1)
- Gartner(1)
- mmsegmentation(1)
- albumentation(1)
- Riemannian metric(1)
- conda(1)
- debugging(1)
- semantic segmentation(1)
- transformers(1)
- AI(1)
- latex(1)
- machine learning(1)
- Riemannian manifold(1)
- Markdown(1)
- poetry(1)
- venv(1)
- vm(1)
- IBM(1)
- mlops(1)
- memo(1)
- vscode(1)
- CV(1)
LEARNING CONTINUOUS REPRESENTATION OF AUDIO FOR ARBITRARY SCALE SUPER RESOLUTION
Review of LEARNING CONTINUOUS REPRESENTATION OF AUDIO FOR ARBITRARY SCALE SUPER RESOLUTION, Jaechang Kim1∗, Yunjoo Lee1∗, Seunghoon hong2, Jungseul Ok
Representation Learning: A Review and New Perspectives in 2012
Representation Learning: A Review and New PerspectivesYoshua Bengio†, Aaron Courville, and Pascal Vincent†Department of computer science and operation
Tensor and Tensor decompositions
From Tamara G. Kolda, Brett W. Bader, Tensor Decompositions and Applications 2009
[REVIEW] Meta-Learning with a Geometry-Adaptive Preconditioner
Suhyun Kang, Duhun Hwang, Moonjung Eo, Taesup Kim, Wonjong Rhee, Meta-Learning with a Geometry-Adaptive Preconditioner, 2023
[REVIEW] Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Chelsea Finn Pieter Abbeel Sergey Levine
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
KeyPoints: - Positional encodeing free hierarchically structured Transformer encoder (resolution independent test/training performance, multiscale fea
Categories of innovation in AI
Gartner suggests that AI innovations in Hype-Cycle down below fall into four categories. 1. Data-centric AI 2. Model-centric AI 3. Applications-centri
Markov decision process
A Markov decision process (MDP) is defined as a stochastic decision-making process that uses a mathematical framework to model the decision-making of
Introduction to Poetry
Poetry, an easy way to build and manage dependencies. (+vscode usage)
Rules of Machine Learning
As your measurements plateau, do not try to solve it from outside of the scope. Refine objectives or product goals.To launch a new model, overal perfo
Opening MLOps
To ensure the model's (service) agility in an inconsistent environment.1\. Server infra: Cloud/ On-premise(Private server)2\. GPU infra: Cloud GPU/ L