The neuroconnectionist research programme

no code implementations • 8 Sep 2022 • Adrien Doerig, Rowan Sommers, Katja Seeliger, Blake Richards, Jenann Ismael, Grace Lindsay, Konrad Kording, Talia Konkle, Marcel A. J. van Gerven, Nikolaus Kriegeskorte, Tim C. Kietzmann

Artificial Neural Networks (ANNs) inspired by biology are beginning to be widely used to model behavioral and neural data, an approach we call neuroconnectionism.

Philosophy

The representation of object drawings and sketches in deep convolutional neural networks

no code implementations • NeurIPS Workshop SVRHM 2020 • Johannes Singer, Katja Seeliger, Martin N Hebart

Further, we show that a texture bias found in CNNs contributes both to the poor classification performance for drawings and the dissimilar representational structure, specifically in the later layers of the network.

Cultural Vocal Bursts Intensity Prediction Object

Generalization of an Upper Bound on the Number of Nodes Needed to Achieve Linear Separability

no code implementations • 10 Feb 2018 • Marjolein Troost, Katja Seeliger, Marcel van Gerven

This will be an upper bound that depends on the structure of the data.

Reconstructing perceived faces from brain activations with deep adversarial neural decoding

no code implementations • NeurIPS 2017 • Yağmur Güçlütürk, Umut Güçlü, Katja Seeliger, Sander Bosch, Rob Van Lier, Marcel A. J. van Gerven

Here, we present a novel approach to solve the problem of reconstructing perceived stimuli from brain responses by combining probabilistic inference with deep learning.

Deep adversarial neural decoding

1 code implementation • 19 May 2017 • Yağmur Güçlütürk, Umut Güçlü, Katja Seeliger, Sander Bosch, Rob Van Lier, Marcel van Gerven

Here, we present a novel approach to solve the problem of reconstructing perceived stimuli from brain responses by combining probabilistic inference with deep learning.