Continual Learning requires the model to learn from a stream of dynamic, non-stationary data without forgetting previous knowledge. Several approaches have been developed in the literature to tackle the Continual Learning challenge. Among them, Replay approaches have empirically proved to be the most effective ones. Replay operates by saving some samples in memory which are then used to rehearse knowledge during training in subsequent tasks. However, an extensive comparison and deeper understanding of different replay implementation subtleties is still missing in the literature. The aim of this work is to compare and analyze existing replay-based strategies and provide practical recommendations on developing efficient, effective and generally applicable replay-based strategies. In particular, we investigate the role of the memory size value, different weighting policies and discuss about the impact of data augmentation, which allows reaching better performance with lower memory sizes.

The National Security Commission on Artificial Intelligence released an interim report on November 4, 2019. The report offers a blend of deservedly bold recommendations coupled with actions that lie within the power of the Executive without all of them involving major funding. The recommendations involve investments in AI R&D; applying AI to national security missions; training and recruiting AI talent; protecting and building upon US technology advantages; and, marshaling global AI cooperation. The Commission may be somewhat less optimistic than warranted with respect to the prospects for the West to share data as US and allies' approaches to preserving privacy are converging. However, the Commission is spot on with respect to the need for high powered diplomacy.

Deep learning neural networks are relatively straightforward to define and train given the wide adoption of open source libraries. Nevertheless, neural networks remain challenging to configure and train. In his 2012 paper titled "Practical Recommendations for Gradient-Based Training of Deep Architectures" published as a preprint and a chapter of the popular 2012 book "Neural Networks: Tricks of the Trade," Yoshua Bengio, one of the fathers of the field of deep learning, provides practical recommendations for configuring and tuning neural network models. In this post, you will step through this long and interesting paper and pick out the most relevant tips and tricks for modern deep learning practitioners. Practical Recommendations for Deep Learning Neural Network Practitioners Photo by Susanne Nilsson, some rights reserved.

Are you promoting AI to consumers, clients or colleagues? If you're in marketing today there is a good chance that you are. But how do you sell artificial intelligence effectively given all the hype and hysteria that surrounds the technology? Here are ten evidence-based recommendations for how to communicate AI effectively from a new Syzygy study that captured people's feelings towards AI across the US, UK, and Germany (n 6000). With all the hype and hysteria around AI, people are suspicious and skeptical.