An overview of model explainability in modern machine learning
Towards a better understanding of why machine learning models make the decisions they do, and why it matters
Link
🔭 @DeepGravity
Towards a better understanding of why machine learning models make the decisions they do, and why it matters
Link
🔭 @DeepGravity
Medium
An overview of model explainability in modern machine learning
How we can understand black box machine learning models, and why it matters
#Bayesian Model Selection: As A Feature Reduction Technique
A gentle introduction to the application of Bayesian Model Selection to identify important features for machine learning model generation.
Article
🔭 @DeepGravity
A gentle introduction to the application of Bayesian Model Selection to identify important features for machine learning model generation.
Article
🔭 @DeepGravity
Medium
Bayesian Model Selection: As A Feature Reduction Technique
A gentle introduction to application of Bayesian Model Selection to identify important features for machine learning model generation.
#Facebook 's Head of #AI Says the Field Will Soon ‘Hit the Wall’
Jerome Pesenti leads the development of artificial intelligence at one of the world’s most influential—and controversial—companies. As VP of artificial intelligence at Facebook, he oversees hundreds of scientists and engineers whose work shapes the company’s direction and its impact on the wider world.
Link
🔭 @DeepGravity
Jerome Pesenti leads the development of artificial intelligence at one of the world’s most influential—and controversial—companies. As VP of artificial intelligence at Facebook, he oversees hundreds of scientists and engineers whose work shapes the company’s direction and its impact on the wider world.
Link
🔭 @DeepGravity
Wired
Facebook's Head of AI Says the Field Will Soon ‘Hit the Wall’
Jerome Pesenti is encouraged by progress in artificial intelligence, but sees the limits of the current approach to deep learning.
Deep Gravity
During the last two days, some famous #MachineLearning researchers elucidated their own definition of #DeepLearning. You might check the related links to read full definitions and discussions on each. Yann LeCun: #DL is constructing networks of parameterized…
👆
Yoshua Bengio:
Deep learning is inspired by neural networks of the brain to build learning machines which discover rich and useful internal representations, computed as a composition of learned features and functions.
Full definition:
https://www.facebook.com/yoshua.bengio/posts/2269432439828350
🔭 @DeepGravity
Yoshua Bengio:
Deep learning is inspired by neural networks of the brain to build learning machines which discover rich and useful internal representations, computed as a composition of learned features and functions.
Full definition:
https://www.facebook.com/yoshua.bengio/posts/2269432439828350
🔭 @DeepGravity
Learning to Navigate Using Mid-Level Visual Priors
Abstract: How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform downstream motor tasks (e.g. navigating a complex environment)? What are the consequences of not utilizing such visual priors in learning? We study these questions by integrating a generic perceptual skill set (a distance estimator, an edge detector, etc.) within a reinforcement learning framework (see Fig. 1). This skill set (“mid-level vision”) provides the policy with a more processed state of the world compared to raw images. Our large-scale study demonstrates that using mid-level vision results in policies that learn faster, generalize better, and achieve higher final performance, when compared to learning from scratch and/or using state-of-the-art visual and nonvisual representation learning methods. We show that conventional computer vision objectives are particularly effective in this regard and can be conveniently integrated into reinforcement learning frameworks. Finally, we found that no single visual representation was universally useful for all downstream tasks, hence we computationally derive a task-agnostic set of representations optimized to support arbitrary downstream tasks.
Link
🔭 @DeepGravity
Abstract: How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform downstream motor tasks (e.g. navigating a complex environment)? What are the consequences of not utilizing such visual priors in learning? We study these questions by integrating a generic perceptual skill set (a distance estimator, an edge detector, etc.) within a reinforcement learning framework (see Fig. 1). This skill set (“mid-level vision”) provides the policy with a more processed state of the world compared to raw images. Our large-scale study demonstrates that using mid-level vision results in policies that learn faster, generalize better, and achieve higher final performance, when compared to learning from scratch and/or using state-of-the-art visual and nonvisual representation learning methods. We show that conventional computer vision objectives are particularly effective in this regard and can be conveniently integrated into reinforcement learning frameworks. Finally, we found that no single visual representation was universally useful for all downstream tasks, hence we computationally derive a task-agnostic set of representations optimized to support arbitrary downstream tasks.
Link
🔭 @DeepGravity
Profillic
Learning to Navigate Using Mid-Level Visual Priors: Model and Code - Profillic
Click To Get Model/Code. How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform downstream motor tasks (e.g. navigating a complex environment)? What are the consequences of not utilizing such…
Deep Gravity
During the last two days, some famous #MachineLearning researchers elucidated their own definition of #DeepLearning. You might check the related links to read full definitions and discussions on each. Yann LeCun: #DL is constructing networks of parameterized…
👆
Danilo J. Rezende: (DeepMind)
DL is a collection of tools to build complex modular differentiable functions. These tools are devoid of meaning, it is pointless to discuss what DL can or cannot do. What gives meaning to it is how it is trained and how the data is fed to it.
https://twitter.com/DeepSpiker/status/1209862283368816641
🔭 @DeepGravity
Danilo J. Rezende: (DeepMind)
DL is a collection of tools to build complex modular differentiable functions. These tools are devoid of meaning, it is pointless to discuss what DL can or cannot do. What gives meaning to it is how it is trained and how the data is fed to it.
https://twitter.com/DeepSpiker/status/1209862283368816641
🔭 @DeepGravity
Twitter
Danilo J. Rezende
Rephrasing @ylecun with my own words: DL is a collection of tools to build complex modular differentiable functions. These tools are devoid of meaning, it is pointless to discuss what DL can or cannot do. What gives meaning to it is how it is trained and…
Deep Gravity
AI Debate 2019: Yoshua Bengio vs Gary Marcus This is an #AI Debate between Yoshua #Bengio and #GaryMarcus from Dec 23, 2019, organized by Montreal.AI and Mila - Institut Québécois d'Intelligence Artificielle. Facebook video: https://www.facebook.com/MontrealAI/v...…
AI Debate 2019 has caused many discussions in both deep learning and cognitive sciences communities about the nature of DL. If you are interested in following these hot discussions, please check Gary Marcus or Yann LeCun recent tweets.
Related links:
https://news.1rj.ru/str/deepgravity/343
https://news.1rj.ru/str/deepgravity/347
https://news.1rj.ru/str/deepgravity/357
https://news.1rj.ru/str/deepgravity/361
🔭 @DeepGravity
Related links:
https://news.1rj.ru/str/deepgravity/343
https://news.1rj.ru/str/deepgravity/347
https://news.1rj.ru/str/deepgravity/357
https://news.1rj.ru/str/deepgravity/361
🔭 @DeepGravity
Telegram
Deep (Learning) Gravity
AI Debate 2019: Yoshua Bengio vs Gary Marcus
This is an #AI Debate between Yoshua #Bengio and #GaryMarcus from Dec 23, 2019, organized by Montreal.AI and Mila - Institut Québécois d'Intelligence Artificielle.
Facebook video: https://www.facebook.com/MontrealAI/v...…
This is an #AI Debate between Yoshua #Bengio and #GaryMarcus from Dec 23, 2019, organized by Montreal.AI and Mila - Institut Québécois d'Intelligence Artificielle.
Facebook video: https://www.facebook.com/MontrealAI/v...…
Crowdfunding Dynamics Tracking: A #ReinforcementLearning Approach
Recent years have witnessed the increasing interests in research of crowdfunding mechanism. In this area, dynamics tracking is a significant issue but is still under exploration. Existing studies either fit the fluctuations of time-series or employ regularization terms to constrain learned tendencies. However, few of them take into account the inherent decision-making process between investors and crowdfunding dynamics. To address the problem, in this paper, we propose a Trajectory-based Continuous Control for Crowdfunding (TC3) algorithm to predict the funding progress in crowdfunding. Specifically, actor-critic frameworks are employed to model the relationship between investors and campaigns, where all of the investors are viewed as an agent that could interact with the environment derived from the real dynamics of campaigns. Then, to further explore the in-depth implications of patterns (i.e., typical characters) in funding series, we propose to subdivide them into fast-growing and slow-growing ones. Moreover, for the purpose of switching from different kinds of patterns, the actor component of TC3 is extended with a structure of options, which comes to the TC3-Options. Finally, extensive experiments on the Indiegogo dataset not only demonstrate the effectiveness of our methods, but also validate our assumption that the entire pattern learned by TC3-Options is indeed the U-shaped one.
Paper
🔭 @DeepGravity
Recent years have witnessed the increasing interests in research of crowdfunding mechanism. In this area, dynamics tracking is a significant issue but is still under exploration. Existing studies either fit the fluctuations of time-series or employ regularization terms to constrain learned tendencies. However, few of them take into account the inherent decision-making process between investors and crowdfunding dynamics. To address the problem, in this paper, we propose a Trajectory-based Continuous Control for Crowdfunding (TC3) algorithm to predict the funding progress in crowdfunding. Specifically, actor-critic frameworks are employed to model the relationship between investors and campaigns, where all of the investors are viewed as an agent that could interact with the environment derived from the real dynamics of campaigns. Then, to further explore the in-depth implications of patterns (i.e., typical characters) in funding series, we propose to subdivide them into fast-growing and slow-growing ones. Moreover, for the purpose of switching from different kinds of patterns, the actor component of TC3 is extended with a structure of options, which comes to the TC3-Options. Finally, extensive experiments on the Indiegogo dataset not only demonstrate the effectiveness of our methods, but also validate our assumption that the entire pattern learned by TC3-Options is indeed the U-shaped one.
Paper
🔭 @DeepGravity
Asymmetric #GAN for Unpaired Image-to-image Translation
Unpaired image-to-image translation problem aims to model the mapping from one domain to another with unpaired training data. Current works like the well-acknowledged Cycle GAN provide a general solution for any two domains through modeling injective mappings with a symmetric structure. While in situations where two domains are asymmetric in complexity, i.e., the amount of information between two domains is different, these approaches pose problems of poor generation quality, mapping ambiguity, and model sensitivity. To address these issues, we propose Asymmetric GAN (AsymGAN) to adapt the asymmetric domains by introducing an auxiliary variable (aux) to learn the extra information for transferring from the information-poor domain to the information-rich domain, which improves the performance of state-of-the-art approaches in the following ways. First, aux better balances the information between two domains which benefits the quality of generation. Second, the imbalance of information commonly leads to mapping ambiguity, where we are able to model one-to-many mappings by tuning aux, and furthermore, our aux is controllable. Third, the training of Cycle GAN can easily make the generator pair sensitive to small disturbances and variations while our model decouples the ill-conditioned relevance of generators by injecting aux during training. We verify the effectiveness of our proposed method both qualitatively and quantitatively on asymmetric situation, label-photo task, on Cityscapes and Helen datasets, and show many applications of asymmetric image translations. In conclusion, our AsymGAN provides a better solution for unpaired image-to-image translation in asymmetric domains.
Paper
🔭 @DeepGravity
Unpaired image-to-image translation problem aims to model the mapping from one domain to another with unpaired training data. Current works like the well-acknowledged Cycle GAN provide a general solution for any two domains through modeling injective mappings with a symmetric structure. While in situations where two domains are asymmetric in complexity, i.e., the amount of information between two domains is different, these approaches pose problems of poor generation quality, mapping ambiguity, and model sensitivity. To address these issues, we propose Asymmetric GAN (AsymGAN) to adapt the asymmetric domains by introducing an auxiliary variable (aux) to learn the extra information for transferring from the information-poor domain to the information-rich domain, which improves the performance of state-of-the-art approaches in the following ways. First, aux better balances the information between two domains which benefits the quality of generation. Second, the imbalance of information commonly leads to mapping ambiguity, where we are able to model one-to-many mappings by tuning aux, and furthermore, our aux is controllable. Third, the training of Cycle GAN can easily make the generator pair sensitive to small disturbances and variations while our model decouples the ill-conditioned relevance of generators by injecting aux during training. We verify the effectiveness of our proposed method both qualitatively and quantitatively on asymmetric situation, label-photo task, on Cityscapes and Helen datasets, and show many applications of asymmetric image translations. In conclusion, our AsymGAN provides a better solution for unpaired image-to-image translation in asymmetric domains.
Paper
🔭 @DeepGravity
A Complete Guide To #Math And #Statistics For #DataScience
Link
Deep (Learning) Gravity, [02.01.20 09:39]
Asymmetric #GAN for Unpaired Image-to-image Translation
Unpaired image-to-image translation problem aims to model the mapping from one domain to another with unpaired training data. Current works like the well-acknowledged Cycle GAN provide a general solution for any two domains through modeling injective mappings with a symmetric structure. While in situations where two domains are asymmetric in complexity, i.e., the amount of information between two domains is different, these approaches pose problems of poor generation quality, mapping ambiguity, and model sensitivity. To address these issues, we propose Asymmetric GAN (AsymGAN) to adapt the asymmetric domains by introducing an auxiliary variable (aux) to learn the extra information for transferring from the information-poor domain to the information-rich domain, which improves the performance of state-of-the-art approaches in the following ways. First, aux better balances the information between two domains which benefits the quality of generation. Second, the imbalance of information commonly leads to mapping ambiguity, where we are able to model one-to-many mappings by tuning aux, and furthermore, our aux is controllable. Third, the training of Cycle GAN can easily make the generator pair sensitive to small disturbances and variations while our model decouples the ill-conditioned relevance of generators by injecting aux during training. We verify the effectiveness of our proposed method both qualitatively and quantitatively on asymmetric situation, label-photo task, on Cityscapes and Helen datasets, and show many applications of asymmetric image translations. In conclusion, our AsymGAN provides a better solution for unpaired image-to-image translation in asymmetric domains.
Paper
🔭 @DeepGravity
Link
Deep (Learning) Gravity, [02.01.20 09:39]
Asymmetric #GAN for Unpaired Image-to-image Translation
Unpaired image-to-image translation problem aims to model the mapping from one domain to another with unpaired training data. Current works like the well-acknowledged Cycle GAN provide a general solution for any two domains through modeling injective mappings with a symmetric structure. While in situations where two domains are asymmetric in complexity, i.e., the amount of information between two domains is different, these approaches pose problems of poor generation quality, mapping ambiguity, and model sensitivity. To address these issues, we propose Asymmetric GAN (AsymGAN) to adapt the asymmetric domains by introducing an auxiliary variable (aux) to learn the extra information for transferring from the information-poor domain to the information-rich domain, which improves the performance of state-of-the-art approaches in the following ways. First, aux better balances the information between two domains which benefits the quality of generation. Second, the imbalance of information commonly leads to mapping ambiguity, where we are able to model one-to-many mappings by tuning aux, and furthermore, our aux is controllable. Third, the training of Cycle GAN can easily make the generator pair sensitive to small disturbances and variations while our model decouples the ill-conditioned relevance of generators by injecting aux during training. We verify the effectiveness of our proposed method both qualitatively and quantitatively on asymmetric situation, label-photo task, on Cityscapes and Helen datasets, and show many applications of asymmetric image translations. In conclusion, our AsymGAN provides a better solution for unpaired image-to-image translation in asymmetric domains.
Paper
🔭 @DeepGravity
DZone
A Complete Guide To Math And Statistics For Data Science
In this article, we provide a comprehensive guide for individuals looking to get started with data science.