This document discusses benchmarking deep learning frameworks like Chainer. It begins by defining benchmarks and their importance for framework developers and users. It then examines examples like convnet-benchmarks, which objectively compares frameworks on metrics like elapsed time. It discusses challenges in accurately measuring elapsed time for neural network functions, particularly those with both Python and GPU components. Finally, it introduces potential solutions like Chainer's Timer class and mentions the DeepMark benchmarks for broader comparisons.
This document summarizes an internship project using deep reinforcement learning to develop an agent that can automatically park a car simulator. The agent takes input from virtual cameras mounted on the car and uses a DQN network to learn which actions to take to reach a parking goal. Several agent configurations were tested, with the three-camera subjective view agent showing the most success after modifications to the reward function and task difficulty via curriculum learning. While the agent could sometimes learn to park, the learning was not always stable, indicating further refinement is needed to the deep RL approach for this automatic parking task.
The document summarizes a meetup discussing deep learning and Docker. It covered Yuta Kashino introducing BakFoo and his background in astrophysics and Python. The meetup discussed recent advances in AI like AlphaGo, generative adversarial networks, and neural style transfer. It provided an overview of Chainer and arXiv papers. The meetup demonstrated Chainer 1.3, NVIDIA drivers, and Docker for deep learning. It showed running a TensorFlow tutorial using nvidia-docker and provided Dockerfile examples and links to resources.
These slides include many inappropriate graphs. If you want to tell the summary of the data correctly, you should avoid to use graphs in this presentation. They can mislead those who view them.
In English, the title of presentaion is "24 slides including graphs that should not be absolutely drawn".
This document discusses benchmarking deep learning frameworks like Chainer. It begins by defining benchmarks and their importance for framework developers and users. It then examines examples like convnet-benchmarks, which objectively compares frameworks on metrics like elapsed time. It discusses challenges in accurately measuring elapsed time for neural network functions, particularly those with both Python and GPU components. Finally, it introduces potential solutions like Chainer's Timer class and mentions the DeepMark benchmarks for broader comparisons.
This document summarizes an internship project using deep reinforcement learning to develop an agent that can automatically park a car simulator. The agent takes input from virtual cameras mounted on the car and uses a DQN network to learn which actions to take to reach a parking goal. Several agent configurations were tested, with the three-camera subjective view agent showing the most success after modifications to the reward function and task difficulty via curriculum learning. While the agent could sometimes learn to park, the learning was not always stable, indicating further refinement is needed to the deep RL approach for this automatic parking task.
The document summarizes a meetup discussing deep learning and Docker. It covered Yuta Kashino introducing BakFoo and his background in astrophysics and Python. The meetup discussed recent advances in AI like AlphaGo, generative adversarial networks, and neural style transfer. It provided an overview of Chainer and arXiv papers. The meetup demonstrated Chainer 1.3, NVIDIA drivers, and Docker for deep learning. It showed running a TensorFlow tutorial using nvidia-docker and provided Dockerfile examples and links to resources.
These slides include many inappropriate graphs. If you want to tell the summary of the data correctly, you should avoid to use graphs in this presentation. They can mislead those who view them.
In English, the title of presentaion is "24 slides including graphs that should not be absolutely drawn".
Japan IBM Middleware User Community (JIMUC) 新春セミナーでの先進IT運用管理分科会の活動報告です。この分科会では Observability 製品:Instana / NewRelic / Datadog の3製品の機能比較をしています。今回はその中間結果をご報告しました。
This study aims to develop an interactive idea-generation support system that enables users to consider the potential side effects of realizing new ideas.
In idea generation, confirmation bias often leads to an excessive focus on ``convenience,'' which can result in the oversight of unintended consequences, referred to as the ``side effects of convenience.''
To address this, we explored methods to alleviate user biases and expand perspectives through system-supported dialogue, facilitating a broader consideration of potential side effects.
The proposed system employs a stepwise idea-generation process supported by large language models (LLMs), enabling users to refine their ideas interactively.
By dividing the ideation process into distinct stages, the system mitigates biases at each stage while promoting ideas' concretization and identifying side effects through visually supported dialogues.
Preliminary evaluation suggests that engaging with the proposed system fosters awareness of diverse perspectives on potential side effects and facilitates the generation of ideas that proactively address these issues.
37. 参考文献
●
K. Simonyan, O. Parkhi, A. Vedaldi, and A. Zisserman. Fisher vector
faces in the wild. BMVC, 2013.
●
Y. Taigman, M. Yang, M. Ranzato, and L. Wolf. DeepFace: Closing the
Gap to Human-Level Performance in Face Verification. CVPR, 2014.
●
N. Dalal, and B. Triggs. Histograms of oriented gradients for human
detection. CVPR, 2005.
●
J. Hays, and A. Efros. Scene completion using millions of photographs.
ACM Transactions on Graphics, Vol. 26, No. 3, 2007.
●
ぱろすけ . 大規模 AV 画像データベースと類似顔画像検索を用いた AV 検索シ
ステム . あの人の研究論文集 , Vol. 3, No. 2, 2012.
●
ぱろすけ . 画像補完技術による衣服の除去 . あの人の研究論文集 , Vol. 4,
No. 2, 2013.