Generative Model

Generative Model with Dynamic Linear Flow

Flow-based generative models are a family of exact log-likelihood models withtractable sampling and latent-variable inference, hence conceptually attractive formodeling complex distributions. However, flow-based models are limited by den-sity estimation performance issues as compared to state-of-the-art autoregressivemodels. Autoregressive models, which also belong to the family of likelihood-based methods, however suffer from limited parallelizability. In this paper, weproposeDynamic Linear Flow (DLF), a new family of invertible transformationswith partially autoregressive structure. Our method benefits from the efficientcomputation of flow-based methods and high density estimation performance ofautoregressive methods. We demonstrate that the proposed DLF yields state-of-the-art performance on ImageNet 32×32 and 64×64 out of all flow-based methods,and is competitive with the best autoregressive model. Additionally, our modelconverges 10 times faster than Glow (Kingma and Dhariwal, 2018). The code isavailable athttps://github.com/naturomics/DLF

deepkapha.ai brings AI to Japan

deepkapha.ai expands its AI services in Japan

Do not miss out on this unique opportunity to get insights from Tarry Singh, leader in AI training and technology. Tarry will share with you his insight and methods for transforming midsize as well as large companies into functioning AI companies in the Europe. Now we are bringing our expertise to Japan! Together with our Country Director we will expand our services in the Japan that will provide enterprise advisory as well as unique AI trainings pertaining to Big Data, Machine Learning and Deep Learning.

Artificial Intelligence training in the Netherlands

AI Training by deepkapha.ai coming to Holland

Do not miss out on this unique opportunity to get insights from Tarry Singh, leader in AI training and technology. Tarry will share with you his insight and methods for transforming midsize as well as large companies into functioning AI companies in the Europe. Now we are bringing our expertise to The Netherlands! We at deepkapha.ai are delighted to announce our AI training partnership with Startel.  Our CEO Tarry Singh and Startel CEO Marco Wagenveld have combined forces to provide unique AI trainings pertaining to Big Data, Machine Learning and Deep Learning.

Generative Model with Dynamic Linear Flow

Generative Model with Dynamic Linear Flow

Flow-based generative models are a family of exact log-likelihood models withtractable sampling and latent-variable inference, hence conceptually attractive formodeling complex distributions. However, flow-based models are limited by den-sity estimation performance issues as compared to state-of-the-art autoregressivemodels. Autoregressive models, which also belong to the family of likelihood-based methods, however suffer from limited parallelizability. In this paper, weproposeDynamic Linear Flow (DLF), a new family of invertible transformationswith partially autoregressive structure. Our method benefits from the efficientcomputation of flow-based methods and high density estimation performance ofautoregressive methods. We demonstrate that the proposed DLF yields state-of-the-art performance on ImageNet 32×32 and 64×64 out of all flow-based methods,and is competitive with the best autoregressive model. Additionally, our modelconverges 10 times faster than Glow (Kingma and Dhariwal, 2018). The code isavailable athttps://github.com/naturomics/DLF

read more
deepkapha.ai expands its AI services in Japan

deepkapha.ai expands its AI services in Japan

Do not miss out on this unique opportunity to get insights from Tarry Singh, leader in AI training and technology. Tarry will share with you his insight and methods for transforming midsize as well as large companies into functioning AI companies in the Europe. Now we are bringing our expertise to Japan! Together with our Country Director we will expand our services in the Japan that will provide enterprise advisory as well as unique AI trainings pertaining to Big Data, Machine Learning and Deep Learning.

read more
AI Training by deepkapha.ai coming to Holland

AI Training by deepkapha.ai coming to Holland

Do not miss out on this unique opportunity to get insights from Tarry Singh, leader in AI training and technology. Tarry will share with you his insight and methods for transforming midsize as well as large companies into functioning AI companies in the Europe. Now we are bringing our expertise to The Netherlands! We at deepkapha.ai are delighted to announce our AI training partnership with Startel.  Our CEO Tarry Singh and Startel CEO Marco Wagenveld have combined forces to provide unique AI trainings pertaining to Big Data, Machine Learning and Deep Learning.

read more
Finland Deep Learning workshop

Finland Deep Learning workshop

deepkapha.ai delivered a 2-day hands-on technical workshop on Deep Learning to some bright minds in Finland. These were from various industry and government areas such as manufacturing, telecom, defense, healthcare and more.

read more
University of Texas, Dallas

University of Texas, Dallas

In this lecture we discussed the newly released capsule network by Geoffrey Hinton and his co-authors. Capsule networks is the new and shiny neural network architecture that is challenging CNN, currently the king of the hill in computer vision.

read more
ICSE Gothenburg, Sweden

ICSE Gothenburg, Sweden

deepkapha.ai was proud to have been both program committee member and presenter at SEC4COG workshop of our breakthrough neuroscience research paper during the 40th International Conference on Software Engineering, May 27 – 3 June 2018, Gothenburg, Sweden.

read more
Meetupai.com Hamburg

Meetupai.com Hamburg

deepkapha.ai was invited to deliver a talk at meetupai.com, a community driven AI Conference setup by Rico Meihl and his associates.

read more

Previous events

Generative Model with Dynamic Linear Flow

Flow-based generative models are a family of exact log-likelihood models withtractable sampling and latent-variable inference, hence conceptually attractive formodeling complex distributions. However, flow-based models are limited by den-sity estimation performance issues as compared to state-of-the-art autoregressivemodels. Autoregressive models, which also belong to the family of likelihood-based methods, however suffer from limited parallelizability. In this paper, weproposeDynamic Linear Flow (DLF), a new family of invertible transformationswith partially autoregressive structure. Our method benefits from the efficientcomputation of flow-based methods and high density estimation performance ofautoregressive methods. We demonstrate that the proposed DLF yields state-of-the-art performance on ImageNet 32×32 and 64×64 out of all flow-based methods,and is competitive with the best autoregressive model. Additionally, our modelconverges 10 times faster than Glow (Kingma and Dhariwal, 2018). The code isavailable athttps://github.com/naturomics/DLF

deepkapha.ai expands its AI services in Japan

Do not miss out on this unique opportunity to get insights from Tarry Singh, leader in AI training and technology. Tarry will share with you his insight and methods for transforming midsize as well as large companies into functioning AI companies in the Europe. Now we are bringing our expertise to Japan! Together with our Country Director we will expand our services in the Japan that will provide enterprise advisory as well as unique AI trainings pertaining to Big Data, Machine Learning and Deep Learning.

AI Training by deepkapha.ai coming to Holland

Do not miss out on this unique opportunity to get insights from Tarry Singh, leader in AI training and technology. Tarry will share with you his insight and methods for transforming midsize as well as large companies into functioning AI companies in the Europe. Now we are bringing our expertise to The Netherlands! We at deepkapha.ai are delighted to announce our AI training partnership with Startel.  Our CEO Tarry Singh and Startel CEO Marco Wagenveld have combined forces to provide unique AI trainings pertaining to Big Data, Machine Learning and Deep Learning.