Semi supervised, weakly-supervised, unsupervised, and active learningYusuke Uchida
?
An overview of semi supervised learning, weakly-supervised learning, unsupervised learning, and active learning.
Focused on recent deep learning-based image recognition approaches.
This document discusses generative adversarial networks (GANs) and their relationship to reinforcement learning. It begins with an introduction to GANs, explaining how they can generate images without explicitly defining a probability distribution by using an adversarial training process. The second half discusses how GANs are related to actor-critic models and inverse reinforcement learning in reinforcement learning. It explains how GANs can be viewed as training a generator to fool a discriminator, similar to how policies are trained in reinforcement learning.
1. The document discusses energy-based models (EBMs) and how they can be applied to classifiers. It introduces noise contrastive estimation and flow contrastive estimation as methods to train EBMs.
2. One paper presented trains energy-based models using flow contrastive estimation by passing data through a flow-based generator. This allows implicit modeling with EBMs.
3. Another paper argues that classifiers can be viewed as joint energy-based models over inputs and outputs, and should be treated as such. It introduces a method to train classifiers as EBMs using contrastive divergence.
[DL輪読会]Neural Radiance Flow for 4D View Synthesis and Video Processing (NeRF...Deep Learning JP
?
Neural Radiance Flow (NeRFlow) is a method that extends Neural Radiance Fields (NeRF) to model dynamic scenes from video data. NeRFlow simultaneously learns two fields - a radiance field to reconstruct images like NeRF, and a flow field to model how points in space move over time using optical flow. This allows it to generate novel views from a new time point. The model is trained end-to-end by minimizing losses for color reconstruction from volume rendering and optical flow reconstruction. However, the method requires training separate models for each scene and does not generalize to unknown scenes.
[DL輪読会]Neural Radiance Flow for 4D View Synthesis and Video Processing (NeRF...Deep Learning JP
?
Neural Radiance Flow (NeRFlow) is a method that extends Neural Radiance Fields (NeRF) to model dynamic scenes from video data. NeRFlow simultaneously learns two fields - a radiance field to reconstruct images like NeRF, and a flow field to model how points in space move over time using optical flow. This allows it to generate novel views from a new time point. The model is trained end-to-end by minimizing losses for color reconstruction from volume rendering and optical flow reconstruction. However, the method requires training separate models for each scene and does not generalize to unknown scenes.
1. A Near-linear Time Approximation
for Angle-based Outlier Detection
in High-dimensional Data [KDD’12]
by N. Pham & R. Pagh Univ. of Copenhagen
発表者:数理情報学専攻 修士2年 山田直敬
1
2. 発表の流れ
1. Outlier Detection in High-dimensional data
- 高次元では次元の呪いによる性能悪化が発生する
2. Angle-based Outlier Detection (ABOD)
- 距離や密度による手法よりも高次元でロバストな手法
3. A Near Linear Time Approximation for ABOD
- ABODの計算量は O(dn3). 近似でこれを大幅に高速化
本論文のcontribution
2
22. 础叠翱顿の近似
ri
?|Lp||Rp| は超平面を跨ぐ回数
b
a
p
? t 回の平均をとることでより精度が高まる.
? F1(p) はMOA1(p)の不偏推定量
?しかも分散も小さいことが示されている. (Chernoff bound)
?L,Rはsortで得る. F1 を求める計算量はO(t n (d+log n) ) 22
29. References [年代順]
1. H.P. Kriegel, M.Schubert, & A. Zimek. Angle-based
outlier detection in high-dimensional data. In KDD
2008.
1. H.P. Kriegel, M. Schubert, & A. Zimek. Outlier
detection techniques. In tutorial at KDD 2010.
1. N. Pham & R. Pagh. A Near-linear Time
Approximation Algorithm for Angle-based Outlier
Detection in High-dimensional Data. In KDD 2012.
29