This document provides an overview of POMDP (Partially Observable Markov Decision Process) and its applications. It first defines the key concepts of POMDP such as states, actions, observations, and belief states. It then uses the classic Tiger problem as an example to illustrate these concepts. The document discusses different approaches to solve POMDP problems, including model-based methods that learn the environment model from data and model-free reinforcement learning methods. Finally, it provides examples of applying POMDP to games like ViZDoom and robot navigation problems.
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.
You Only Look One-level Featureの解説と見せかけた物体検出のよもやま話Yusuke Uchida
第7回全日本コンピュータビジョン勉強会「CVPR2021読み会」(前編)の発表資料です
https://kantocv.connpass.com/event/216701/
You Only Look One-level Featureの解説と、YOLO系の雑談や、物体検出における関連する手法等を広く説明しています
This document summarizes recent research on applying self-attention mechanisms from Transformers to domains other than language, such as computer vision. It discusses models that use self-attention for images, including ViT, DeiT, and T2T, which apply Transformers to divided image patches. It also covers more general attention modules like the Perceiver that aims to be domain-agnostic. Finally, it discusses work on transferring pretrained language Transformers to other modalities through frozen weights, showing they can function as universal computation engines.
You Only Look One-level Featureの解説と見せかけた物体検出のよもやま話Yusuke Uchida
第7回全日本コンピュータビジョン勉強会「CVPR2021読み会」(前編)の発表資料です
https://kantocv.connpass.com/event/216701/
You Only Look One-level Featureの解説と、YOLO系の雑談や、物体検出における関連する手法等を広く説明しています
This document summarizes recent research on applying self-attention mechanisms from Transformers to domains other than language, such as computer vision. It discusses models that use self-attention for images, including ViT, DeiT, and T2T, which apply Transformers to divided image patches. It also covers more general attention modules like the Perceiver that aims to be domain-agnostic. Finally, it discusses work on transferring pretrained language Transformers to other modalities through frozen weights, showing they can function as universal computation engines.
KCS AI班2017年2月22日の活動。
“Why Should I Trust You?” Explaining the Predictions of Any Classifier (Ribeiro et al., 2016)の紹介。
機械学習のモデルの解釈可能な根拠を提示する手法「LIME」の論文。
Response Summarizer: An Automatic Summarization System of Call Center Convers...Preferred Networks
1. The document proposes an automatic summarization system for call center conversations that extracts a one sentence summary of the customer's problem report and a summary of the operator's response within a predetermined number of characters.
2. The system analyzes conversational data to understand important utterances, then scores words and extracts summaries using techniques like dynamic programming. It was tested on call center data and achieved a 81% accuracy rate for customer summaries and up to a 64% ROUGE score for operator summaries.
3. While sentence extraction performed better than compression for evaluation, compression that also incorporated scoring of words based on features like stop words and utterance position performed best for the ROUGE evaluation metric. The system shows potential for
This document describes a summer internship project using chatbots to sell products online. The intern developed a neural sequence-to-sequence model with attention to generate sentences explaining the attractiveness of travel spots in Japan based on their features. The model was trained on over 144,000 sentences from a travel curation website describing spots and reasons to visit them. It can generate sentences explaining why a spot is recommended based on its features, or reverse the input and output to explain the features based on the reasons. The intern believes attention mechanisms work well and future work could involve linking the model to a knowledge base or using reinforcement learning with user feedback.
Generation of 3D-avatar animation from latent representationsPreferred Networks
This document summarizes an internship project to generate 3D avatar animations from latent representations. The intern aimed to manipulate robots through natural language by utilizing 3D avatar motion data provided by DeNA. Experiments using autoencoders and principal component analysis (PCA) found that PCA performed best, able to compress the high-dimensional motion data into 30 dimensions with less than 1% error. The conclusion is that linear dimension reduction methods like PCA can highly compress motion data, and each dimension of the resulting latent representations may correspond to meaningful motions like floating or squatting.
Tutorial of topological_data_analysis_part_1(basic)Ha Phuong
This document provides an overview of topological data analysis (TDA) concepts, including:
- Simplicial complexes which represent topological spaces and holes of different dimensions
- Persistent homology which tracks the appearance and disappearance of holes over different scales
- Applications of TDA concepts like using persistent homology to analyze protein compressibility.
This document discusses Bayesian dark knowledge and matrix factorization using stochastic gradient MCMC methods. It applies various SG-MCMC methods like SGLD, SG-HMC, and SG-NHT to Bayesian dark knowledge. It also combines GANs with Bayesian dark knowledge to generate unlabeled data. Finally, it applies SG-MCMC and neural networks to probabilistic matrix factorization. Results on MNIST and movie recommendation datasets are presented.
論文紹介:Dueling network architectures for deep reinforcement learningKazuki Adachi
Wang, Ziyu, et al. "Dueling network architectures for deep reinforcement learning." Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:1995-2003, 2016.
7月29日開催 July Tech Festa 2018基調講演スライドです。
大村伸吾「Preferred Networksの機械学習クラスタを支える技術」
https://2018.techfesta.jp/
Slides of Keynote in July Tech Festa 2018.
Soft Actor-Critic is an off-policy maximum entropy deep reinforcement learning algorithm that uses a stochastic actor. It was presented in a 2017 NIPS paper by researchers from OpenAI, UC Berkeley, and DeepMind. Soft Actor-Critic extends the actor-critic framework by incorporating an entropy term into the reward function to encourage exploration. This allows the agent to learn stochastic policies that can operate effectively in environments with complex, sparse rewards. The algorithm was shown to learn robust policies on continuous control tasks using deep neural networks to approximate the policy and action-value functions.