Large-scale Distributed Optimization
One approach inspired by human intelligence is the idea that complex thinking and decision-making are often distributed. Since humans...
The future of AI for decision-making
In their latest blog posts, our experts explain where we are travelling to- and where we are coming from
PredApp
- Jun 18, 2020
- 7 min
Stochastic Network Control
How can you make the best business decisions to optimize the balance between cost and quality? Most organizations apply a trade-off...
1,048 views
PredApp
- Mar 11, 2020
- 4 min
How AI should and can cope with multiplying agents?
Certain phenomena underlie the dynamics of complex environments, whether they are natural weather systems and epidemics; designed...
21 views
PredApp
- Sep 8, 2019
- 3 min
How much computation do Gaussian Processes really need?
At Predapp we are not afraid to tackle the problems other common machine learning methods (like deep learning) find difficult. We...
60 views
PredApp
- Aug 13, 2019
- 5 min
How AI solutions can triumph over the human mind?
As the world grows ever more interconnected and complex, making good decisions becomes increasingly difficult – and necessary....
4 views
PredApp
- Jun 18, 2019
- 6 min
Social AI and Principled AI for Decision Making
Intelligent agents are all around us: under Netflix’s movie suggestions; behind Siri’s weather forecasts; inside car suspensions and...
2 views
PredApp
- Oct 9, 2018
- 5 min
Probabilistic models as basis for for principled AI decision-making
Predapp’s platform uses autonomous AI agents that make decisions based on mathematical principles. Probabilistic modelling underpins...
2 views
PredApp
- Aug 8, 2018
- 2 min
Training with marginal likelihood
Data augmentation aims to make the predictions of the classification system insensitive to modifications of the input that do not change...
3 views
PredApp
- Feb 7, 2018
- 5 min
What is Principled AI?
We at Predapp think of ourselves as the Principled AI company. It’s a phrase that some people outside of the industry might find a bit...
1 view
PredApp
- Oct 9, 2017
- 6 min
Approximate the posterior not the model
Many people like to use Gaussian process (GP) models. Even the most expert deep learning researchers will use a GP for regression...
8 views