Creating A Character in Uncharted: Drake's FortuneNaughty Dog
Christian Gyrling is a programmer at Naughty Dog who created the enemy characters and co-authored the AI in Uncharted: Drake's Fortune. He discusses the challenges of creating many complex animations for the new console generation. To address these challenges, Naughty Dog used additive animations to preserve base animations while adding variations like aiming and looking. They also streamlined the animation workflow and built a test bed to quickly iterate. This allowed for great variety in enemy movements and reactions without much additional programming complexity.
Creating A Character in Uncharted: Drake's FortuneNaughty Dog
Christian Gyrling is a programmer at Naughty Dog who created the enemy characters and co-authored the AI in Uncharted: Drake's Fortune. He discusses the challenges of creating many complex animations for the new console generation. To address these challenges, Naughty Dog used additive animations to preserve base animations while adding variations like aiming and looking. They also streamlined the animation workflow and built a test bed to quickly iterate. This allowed for great variety in enemy movements and reactions without much additional programming complexity.
Zaikun Xu from the Università della Svizzera Italiana presented this deck at the 2016 Switzerland HPC Conference.
“In the past decade, deep learning as a life-changing technology, has gained a huge success on various tasks, including image recognition, speech recognition, machine translation, etc. Pio- neered by several research groups, Geoffrey Hinton (U Toronto), Yoshua Benjio (U Montreal), Yann LeCun(NYU), Juergen Schmiduhuber (IDSIA, Switzerland), Deep learning is a renaissance of neural network in the Big data era.
Neural network is a learning algorithm that consists of input layer, hidden layers and output layers, where each circle represents a neural and the each arrow connection associates with a weight. The way neural network learns is based on how different between the output of output layer and the ground truth, following by calculating the gradients of this discrepancy w.r.b to the weights and adjust the weight accordingly. Ideally, it will find weights that maps input X to target y with error as lower as possible.”
Watch the video presentation: http://insidehpc.com/2016/03/deep-learning/
See more talks in the Swiss Conference Video Gallery: http://insidehpc.com/2016-swiss-hpc-conference/
Sign up for our insideHPC Newsletter: http://insidehpc.com/newsletter
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.
안녕하세요.
강화학습을 공부하면서 처음 접하시는 분들을 위해 ppt로 '강화학습의 개요'에 대해서 정리했습니다.
동물이 학습하는 것과 똑같이 시행착오를 겪으면서 학습하는 강화학습은 기계학습 분야에서 상당히 매력적이라고 생각합니다.
https://www.youtube.com/watch?v=PQtDTdDr8vs&feature=youtu.be
위의 링크는 스키너의 쥐 실험 영상입니다.
감사합니다.
The document contains mathematical equations and notation related to machine learning and probability distributions. It involves defining terms like P(y|x), which represents the probability of outcome y given x, and exploring ways to calculate the expected value of an objective function Rn under different probability distributions p and q over the variables x and y. The goal appears to be to select parameters θ to optimize some objective while accounting for the distributions of the training data.
Built for performance: the UIElements Renderer – Unite Copenhagen 2019Unity Technologies
In this technical talk, we will describe the science behind the UIElements rendering system, built from the ground up for retained-mode UI. It uses every CPU/GPU trick in the book to render thousands of different elements onscreen in a fraction of a millisecond, all on one thread. This powerful UI performance and optimization tool also supports complex features like clipping and vector graphics, even on low-end devices.
Speaker: Wessam Bahnassi – Unity
Watch the session on YouTube: https://youtu.be/zeCdVmfGUN0
Bill explains some of the ways that the Vertex Shader can be used to improve performance by taking a fast path through the Vertex Shader rather than generating vertices with other parts of the pipeline in this AMD technology presentation from the 2014 Game Developers Conference in San Francisco March 17-21. Check out more technical presentations at http://developer.amd.com/resources/documentation-articles/conference-presentations/
* Satoshi Hara and Kohei Hayashi. Making Tree Ensembles Interpretable: A Bayesian Model Selection Approach. AISTATS'18 (to appear).
arXiv ver.: https://arxiv.org/abs/1606.09066#
* GitHub
https://github.com/sato9hara/defragTrees
Ever wondered how to use modern OpenGL in a way that radically reduces driver overhead? Then this talk is for you.
John McDonald and Cass Everitt gave this talk at Steam Dev Days in Seattle on Jan 16, 2014.
A technical deep dive into the DX11 rendering in Battlefield 3, the first title to use the new Frostbite 2 Engine. Topics covered include DX11 optimization techniques, efficient deferred shading, high-quality rendering and resource streaming for creating large and highly-detailed dynamic environments on modern PCs.
Zaikun Xu from the Università della Svizzera Italiana presented this deck at the 2016 Switzerland HPC Conference.
“In the past decade, deep learning as a life-changing technology, has gained a huge success on various tasks, including image recognition, speech recognition, machine translation, etc. Pio- neered by several research groups, Geoffrey Hinton (U Toronto), Yoshua Benjio (U Montreal), Yann LeCun(NYU), Juergen Schmiduhuber (IDSIA, Switzerland), Deep learning is a renaissance of neural network in the Big data era.
Neural network is a learning algorithm that consists of input layer, hidden layers and output layers, where each circle represents a neural and the each arrow connection associates with a weight. The way neural network learns is based on how different between the output of output layer and the ground truth, following by calculating the gradients of this discrepancy w.r.b to the weights and adjust the weight accordingly. Ideally, it will find weights that maps input X to target y with error as lower as possible.”
Watch the video presentation: http://insidehpc.com/2016/03/deep-learning/
See more talks in the Swiss Conference Video Gallery: http://insidehpc.com/2016-swiss-hpc-conference/
Sign up for our insideHPC Newsletter: http://insidehpc.com/newsletter
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.
안녕하세요.
강화학습을 공부하면서 처음 접하시는 분들을 위해 ppt로 '강화학습의 개요'에 대해서 정리했습니다.
동물이 학습하는 것과 똑같이 시행착오를 겪으면서 학습하는 강화학습은 기계학습 분야에서 상당히 매력적이라고 생각합니다.
https://www.youtube.com/watch?v=PQtDTdDr8vs&feature=youtu.be
위의 링크는 스키너의 쥐 실험 영상입니다.
감사합니다.
The document contains mathematical equations and notation related to machine learning and probability distributions. It involves defining terms like P(y|x), which represents the probability of outcome y given x, and exploring ways to calculate the expected value of an objective function Rn under different probability distributions p and q over the variables x and y. The goal appears to be to select parameters θ to optimize some objective while accounting for the distributions of the training data.
Built for performance: the UIElements Renderer – Unite Copenhagen 2019Unity Technologies
In this technical talk, we will describe the science behind the UIElements rendering system, built from the ground up for retained-mode UI. It uses every CPU/GPU trick in the book to render thousands of different elements onscreen in a fraction of a millisecond, all on one thread. This powerful UI performance and optimization tool also supports complex features like clipping and vector graphics, even on low-end devices.
Speaker: Wessam Bahnassi – Unity
Watch the session on YouTube: https://youtu.be/zeCdVmfGUN0
Bill explains some of the ways that the Vertex Shader can be used to improve performance by taking a fast path through the Vertex Shader rather than generating vertices with other parts of the pipeline in this AMD technology presentation from the 2014 Game Developers Conference in San Francisco March 17-21. Check out more technical presentations at http://developer.amd.com/resources/documentation-articles/conference-presentations/
* Satoshi Hara and Kohei Hayashi. Making Tree Ensembles Interpretable: A Bayesian Model Selection Approach. AISTATS'18 (to appear).
arXiv ver.: https://arxiv.org/abs/1606.09066#
* GitHub
https://github.com/sato9hara/defragTrees
Ever wondered how to use modern OpenGL in a way that radically reduces driver overhead? Then this talk is for you.
John McDonald and Cass Everitt gave this talk at Steam Dev Days in Seattle on Jan 16, 2014.
A technical deep dive into the DX11 rendering in Battlefield 3, the first title to use the new Frostbite 2 Engine. Topics covered include DX11 optimization techniques, efficient deferred shading, high-quality rendering and resource streaming for creating large and highly-detailed dynamic environments on modern PCs.
[paper review] 손규빈 - Eye in the sky & 3D human pose estimation in video with ...Gyubin Son
1. Eye in the Sky: Real-time Drone Surveillance System (DSS) for Violent Individuals Identification using ScatterNet Hybrid Deep Learning Network
https://arxiv.org/abs/1806.00746
2. 3D human pose estimation in video with temporal convolutions and semi-supervised training
https://arxiv.org/abs/1811.11742
20. 불량타입 총 8가지
• Center
• Donut
• Edge-Loc
• Edge-Ring
• Loc
• Random
• Scratch
• Near-full
21. 데이터 불균형 문제가 존재
데이터 확대의 필요성
Convolutional Autoencoder를 이용
22. Autoencoder Generative Adversarial Networks
차원이 적은 데이터가 있어도 다시 복원할 수
있도록 특징을 찾아내는 것이 목표.
영상 의학 분야 등 아직 데이터 수가 충분하지
않은 분야에서 사용.
부족한 학습 데이터 수를 효과적으로 늘려주는
효과.
임의의 Noise로부터 리얼한 영상을 만들어 내
는 신경망.
결과는 매우 뚜렷. 실제같음. 완전한 가상의 이
미지를 만들어냄.
Autoencoder선택
35. 연구결과에 대한 신한정밀공업(주)의 입장
신한정밀공업(주)는 현대모비스에 자동차부품을 공급하는 업체로서,
내연기관에서 전기차생산으로 바뀌는 자동차업계의 흐름에 올라타, 전기차시장에서 선두주자가 되고자한다.
이번 연구성과는, 자동차 반도체를 공급할 때, 관련 업계에 매우 유용한 서비스로 간주 됨에 따라,
반도체업계에서 반도체 수율을 높이는 새로운 Innovative algorithms 으로써 고려할 수 있음