`

Timezone: »

 
Spotlight
A Theoretical Framework for Target Propagation
Alexander Meulemans · Francesco Carzaniga · Johan Suykens · João Sacramento · Benjamin F. Grewe

Tue Dec 08 07:30 AM -- 07:40 AM (PST) @ Orals & Spotlights: Dynamical Sys/Density/Sparsity

The success of deep learning, a brain-inspired form of AI, has sparked interest in understanding how the brain could similarly learn across multiple layers of neurons. However, the majority of biologically-plausible learning algorithms have not yet reached the performance of backpropagation (BP), nor are they built on strong theoretical foundations. Here, we analyze target propagation (TP), a popular but not yet fully understood alternative to BP, from the standpoint of mathematical optimization. Our theory shows that TP is closely related to Gauss-Newton optimization and thus substantially differs from BP. Furthermore, our analysis reveals a fundamental limitation of difference target propagation (DTP), a well-known variant of TP, in the realistic scenario of non-invertible neural networks. We provide a first solution to this problem through a novel reconstruction loss that improves feedback weight training, while simultaneously introducing architectural flexibility by allowing for direct feedback connections from the output to each hidden layer. Our theory is corroborated by experimental results that show significant improvements in performance and in the alignment of forward weight updates with loss gradients, compared to DTP.

Author Information

Alexander Meulemans (ETH Zürich | University of Zürich | Institute of Neuroinformatics)
Francesco Carzaniga (Institute of Neuroinformatics, University of Zurich and ETH Zurich)
Johan Suykens (KU Leuven)
João Sacramento (ETH Zurich)
Benjamin F. Grewe (ETH Zurich)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors