DeepAI AI Chat
Log In Sign Up

Learning Abstract Classes using Deep Learning

by   Sebastian Stabinger, et al.
Leopold Franzens Universität Innsbruck

Humans are generally good at learning abstract concepts about objects and scenes (e.g. spatial orientation, relative sizes, etc.). Over the last years convolutional neural networks have achieved almost human performance in recognizing concrete classes (i.e. specific object categories). This paper tests the performance of a current CNN (GoogLeNet) on the task of differentiating between abstract classes which are trivially differentiable for humans. We trained and tested the CNN on the two abstract classes of horizontal and vertical orientation and determined how well the network is able to transfer the learned classes to other, previously unseen objects.


page 3

page 4


Evaluation of Deep Learning on an Abstract Image Classification Dataset

Convolutional Neural Networks have become state of the art methods for i...

25 years of CNNs: Can we compare to human abstraction capabilities?

We try to determine the progress made by convolutional neural networks o...

Can We Teach Computers to Understand Art? Domain Adaptation for Enhancing Deep Networks Capacity to De-Abstract Art

Humans comprehend a natural scene at a single glance; painters and other...

Computer Viruses: The Abstract Theory Revisited

Identifying new viral threats, and developing long term defences against...

A Provable Defense for Deep Residual Networks

We present a training system, which can provably defend significantly la...

On the safety of vulnerable road users by cyclist orientation detection using Deep Learning

In this work, orientation detection using Deep Learning is acknowledged ...

How do we get there? Evaluating transformer neural networks as cognitive models for English past tense inflection

There is an ongoing debate on whether neural networks can grasp the quas...