Fixing Bugs with Deep Learning

In a new paper, Self-Supervised Bug Detection and Repair, presented at the 2021 Conference on Neural Information Processing Systems (NeurIPS 2021), Microsoft show a promising deep learning model, called BugLab.

BugLab can be taught to detect and fix bugs, without using labelled data, through a “hide and seek” game. The goal of our work is to develop better AI that can automatically find and repair bugs.

BugLab uses two competing models that learn by playing a “hide and seek” game that is broadly inspired by generative adversarial networks (GAN).

For some samples, please check out the Microsoft blog at the link below.

Links:

• https://www.microsoft.com/en-us/research/blog/finding-and-fixing-bugs-with-deep-learning/
  

Slaughterbots

 

This is video to demonstrate how dangerous "Smart Weapon" is. And if this isn't what you want, please take action at http://autonomousweapons.org/

Links:

• KARGU - Autonomous Tactical Multi-Rotor Attack UAV - https://www.youtube.com/watch?v=Oqv9yaPLhEk
• STM KARGU (Autonomous Tactical Multi-Rotor Attack UAV) - https://www.youtube.com/watch?v=9HCDQwRdk20
• https://buzzorange.com/citiorange/2021/12/07/killer-robots/ 
  

 

Estimation, Prediction and Forecasting

What's the quick distinction among Estimation, Prediction and Forecasting.

First, Estimation Vs Prediction.

Estimation is after occurrence of the event i.e. posterior probability; while Prediction is a kind of estimation before the occurrence of the event i.e. apriori probability.

Estimation implies finding the optimal parameter using historical data whereas prediction uses the data to compute the random value of the unseen data.

Second, what is Forecasting.

Forecasting is a subset of prediction wherein both use the historical data and estimating about the future events. And the difference between forecasting and prediction is the explicit addition of temporal dimension in forecasting.

Forecasting is a time-based prediction i.e. it is more appropriate while dealing with time series data. Prediction, on the other hand, need not be time based only, it can be based on multiple casual factors that influence the target variable.