DNN Architecture for High Performance Prediction on Natural Videos Loses Submodule's Ability to Learn Discrete-World Dataset

04/16/2019
by   Lana Sinapayen, et al.
0

Is cognition a collection of loosely connected functions tuned to different tasks, or can there be a general learning algorithm? If such an hypothetical general algorithm did exist, tuned to our world, could it adapt seamlessly to a world with different laws of nature? We consider the theory that predictive coding is such a general rule, and falsify it for one specific neural architecture known for high-performance predictions on natural videos and replication of human visual illusions: PredNet. Our results show that PredNet's high performance generalizes without retraining on a completely different natural video dataset. Yet PredNet cannot be trained to reach even mediocre accuracy on an artificial video dataset created with the rules of the Game of Life (GoL). We also find that a submodule of PredNet, a Convolutional Neural Network trained alone, reaches perfect accuracy on the GoL while being mediocre for natural videos, showing that PredNet's architecture itself is responsible for both the high performance on natural videos and the loss of performance on the GoL. Just as humans cannot predict the dynamics of the GoL, our results suggest that there might be a trade-off between high performance on sensory inputs with different sets of rules.

READ FULL TEXT

page 4

page 5

page 7

research
05/25/2016

Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning

While great strides have been made in using deep learning algorithms to ...
research
05/22/2021

Soccer Player Tracking in Low Quality Video

In this paper we propose a system capable of tracking multiple soccer pl...
research
04/29/2020

Deepfake Video Forensics based on Transfer Learning

Deeplearning has been used to solve complex problems in various domains....
research
12/03/2020

Reconstructing cellular automata rules from observations at nonconsecutive times

Recent experiments by Springer and Kenyon have shown that a deep neural ...
research
02/11/2015

Large-Scale Deep Learning on the YFCC100M Dataset

We present a work-in-progress snapshot of learning with a 15 billion par...
research
11/19/2015

Unsupervised Learning of Visual Structure using Predictive Generative Networks

The ability to predict future states of the environment is a central pil...
research
03/02/2021

Task-Adaptive Neural Network Retrieval with Meta-Contrastive Learning

Most conventional Neural Architecture Search (NAS) approaches are limite...

Please sign up or login with your details

Forgot password? Click here to reset