Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Jannik Kossen

Jannik Kossen

Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task

Nov 09, 2022
Jannik Kossen, Cătălina Cangea, Eszter Vértes, Andrew Jaegle, Viorica Patraucean, Ira Ktena, Nenad Tomasev, Danielle Belgrave

Figure 1 for Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task

Figure 2 for Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task

Figure 3 for Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task

Figure 4 for Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task

* Foundation Models for Decision Making Workshop at Neural Information Processing Systems 2022

Access Paper or Ask Questions

Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling

May 18, 2022
Andreas Kirsch, Jannik Kossen, Yarin Gal

Figure 1 for Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling

Figure 2 for Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling

* 10 pages + references

Access Paper or Ask Questions

Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning

Jun 04, 2021
Jannik Kossen, Neil Band, Clare Lyle, Aidan N. Gomez, Tom Rainforth, Yarin Gal

Figure 1 for Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning

Figure 2 for Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning

Figure 3 for Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning

Figure 4 for Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning

* First two authors contributed equally

Access Paper or Ask Questions