Tim C. Kietzmann

Adrien Doerig, Tim C Kietzmann, Emily Allen et al.

The human brain extracts complex information from visual inputs, including objects, their spatial and semantic interrelations, and their interactions with the environment. However, a quantitative approach for studying this information remains elusive. Here, we test whether the contextual information encoded in large language models (LLMs) is beneficial for modelling the complex visual information extracted by the brain from natural scenes. We show that LLM embeddings of scene captions successfully characterise brain activity evoked by viewing the natural scenes. This mapping captures selectivities of different brain areas, and is sufficiently robust that accurate scene captions can be reconstructed from brain activity. Using carefully controlled model comparisons, we then proceed to show that the accuracy with which LLM representations match brain representations derives from the ability of LLMs to integrate complex information contained in scene captions beyond that conveyed by individual words. Finally, we train deep neural network models to transform image inputs into LLM representations. Remarkably, these networks learn representations that are better aligned with brain representations than a large number of state-of-the-art alternative models, despite being trained on orders-of-magnitude less data. Overall, our results suggest that LLM embeddings of scene captions provide a representational format that accounts for complex information extracted by the brain from visual inputs.

Zejin Lu, Adrien Doerig, Victoria Bosch et al.

Computational models are an essential tool for understanding the origin and functions of the topographic organisation of the primate visual system. Yet, vision is most commonly modelled by convolutional neural networks that ignore topography by learning identical features across space. Here, we overcome this limitation by developing All-Topographic Neural Networks (All-TNNs). Trained on visual input, several features of primate topography emerge in All-TNNs: smooth orientation maps and cortical magnification in their first layer, and category-selective areas in their final layer. In addition, we introduce a novel dataset of human spatial biases in object recognition, which enables us to directly link models to behaviour. We demonstrate that All-TNNs significantly better align with human behaviour than previous state-of-the-art convolutional models due to their topographic nature. All-TNNs thereby mark an important step forward in understanding the spatial organisation of the visual brain and how it mediates visual behaviour.

Sushrut Thorat, Adrien Doerig, Tim C. Kietzmann

Recurrent neural networks (RNNs) have yielded promising results for both recognizing objects in challenging conditions and modeling aspects of primate vision. However, the representational dynamics of recurrent computations remain poorly understood, especially in large-scale visual models. Here, we studied such dynamics in RNNs trained for object classification on MiniEcoset, a novel subset of ecoset. We report two main insights. First, upon inference, representations continued to evolve after correct classification, suggesting a lack of the notion of being ``done with classification''. Second, focusing on ``readout zones'' as a way to characterize the activation trajectories, we observe that misclassified representations exhibit activation patterns with lower L2 norm, and are positioned more peripherally in the readout zones. Such arrangements help the misclassified representations move into the correct zones as time progresses. Our findings generalize to networks with lateral and top-down connections, and include both additive and multiplicative interactions with the bottom-up sweep. The results therefore contribute to a general understanding of RNN dynamics in naturalistic tasks. We hope that the analysis framework will aid future investigations of other types of RNNs, including understanding of representational dynamics in primate vision.

Daniel Anthes, Sushrut Thorat, Peter König et al.

Unlike primates, training artificial neural networks on changing data distributions leads to a rapid decrease in performance on old tasks. This phenomenon is commonly referred to as catastrophic forgetting. In this paper, we investigate the representational changes that underlie this performance decrease and identify three distinct processes that together account for the phenomenon. The largest component is a misalignment between hidden representations and readout layers. Misalignment occurs due to learning on additional tasks and causes internal representations to shift. Representational geometry is partially conserved under this misalignment and only a small part of the information is irrecoverably lost. All types of representational changes scale with the dimensionality of hidden representations. These insights have implications for deep learning applications that need to be continuously updated, but may also aid aligning ANN models to the rather robust biological vision.

Victoria Bosch, Rowan Sommers, Adrien Doerig et al.

Recent studies reveal striking representational alignment between artificial neural networks (ANNs) and biological brains, leading to proposals that all sufficiently capable systems converge on universal representations of reality. Here, we argue that this claim of Universality is premature. We introduce the Umwelt Representation Hypothesis (URH), proposing that alignment arises not from convergence toward a single global optimum, but from overlap in ecological constraints under which systems develop. We review empirical evidence showing that representational differences between species, individuals, and ANNs are systematic and adaptive, which is difficult to reconcile with Universality. Finally, we reframe ANN model comparison as a method for mapping clusters of alignment in ecological constraint space rather than searching for a single optimal world model.

Daniel Anthes, Sushrut Thorat, Peter König et al.

Continual learning algorithms strive to acquire new knowledge while preserving prior information. Often, these algorithms emphasise stability and restrict network updates upon learning new tasks. In many cases, such restrictions come at a cost to the model's plasticity, i.e. the model's ability to adapt to the requirements of a new task. But is all change detrimental? Here, we approach this question by proposing that activation spaces in neural networks can be decomposed into two subspaces: a readout range in which change affects prior tasks and a null space in which change does not alter prior performance. Based on experiments with this novel technique, we show that, indeed, not all activation change is associated with forgetting. Instead, only change in the subspace visible to the readout of a task can lead to decreased stability, while restricting change outside of this subspace is associated only with a loss of plasticity. Analysing various commonly used algorithms, we show that regularisation-based techniques do not fully disentangle the two spaces and, as a result, restrict plasticity more than need be. We expand our results by investigating a linear model in which we can manipulate learning in the two subspaces directly and thus causally link activation changes to stability and plasticity. For hierarchical, nonlinear cases, we present an approximation that enables us to estimate functionally relevant subspaces at every layer of a deep nonlinear network, corroborating our previous insights. Together, this work provides novel means to derive insights into the mechanisms behind stability and plasticity in continual learning and may serve as a diagnostic tool to guide developments of future continual learning algorithms that stabilise inference while allowing maximal space for learning.

Linda Ariel Ventura, Victoria Bosch, Tim C Kietzmann et al.

Adaptive cognition requires structured internal models representing objects and their relations. Predictive neural networks are often proposed to form such "world models", yet their underlying mechanisms remain unclear. One hypothesis is that action-conditioned sequential prediction suffices for learning such world models. In this work, we investigate this possibility in a minimal in-silico setting. Sequentially sampling tokens from 2D continuous token scenes, a recurrent neural network is trained to predict the upcoming token from current input and a saccade-like displacement. On novel scenes, prediction accuracy improves across the sequence, indicating in-context learning. Decoding analyses reveal path integration and dynamic binding of token identity to position. Interventional analyses show that new bindings can be learned late in sequence and that out-of-distribution bindings can be learned. Together, these results demonstrate how structured representations that rely on flexible binding emerge to support prediction, offering a mechanistic account of sequential world modeling relevant to cognitive science.

Zejin Lu, Sushrut Thorat, Radoslaw M Cichy et al.

Despite years of research and the dramatic scaling of artificial intelligence (AI) systems, a striking misalignment between artificial and human vision persists. Contrary to humans, AI heavily relies on texture-features rather than shape information, lacks robustness to image distortions, remains highly vulnerable to adversarial attacks, and struggles to recognise simple abstract shapes within complex backgrounds. To close this gap, we here introduce a solution that arises from a previously underexplored direction: rather than scaling up, we take inspiration from how human vision develops from early infancy into adulthood. We quantified the visual maturation by synthesising decades of psychophysical and neurophysiological research into a novel developmental visual diet (DVD) for AI vision. We show that guiding AI systems through this human-inspired curriculum produces models that closely align with human behaviour on every hallmark of robust vision tested yielding the strongest reported reliance on shape information to date, abstract shape recognition beyond the state of the art, higher robustness to image corruptions, and stronger resilience to adversarial attacks. By outperforming high parameter AI foundation models trained on orders of magnitude more data, we provide evidence that robust AI vision can be achieved by guiding the way how a model learns, not merely how much it learns, offering a resource-efficient route toward safer and more human-like artificial visual systems.

Rowan P. Sommers, Sushrut Thorat, Daniel Anthes et al.

Flexible cognition demands discovering hidden rules to quickly adapt stimulus-response mappings. Standard neural networks struggle in such tasks requiring rapid, context-driven remapping. Recently, Hummos (2023) introduced a fast-and-slow learning algorithm to mitigate this shortcoming, but its scalability to complex, image-computable tasks was unclear. Here, we propose the Wisconsin Neural Network (WiNN), which extends Hummos' fast-and-slow learning to image-computable tasks demanding flexible rule-based behavior. WiNN employs a pretrained convolutional neural network for vision, coupled with an adjustable "context state" that guides attention to relevant features. If WiNN produces an incorrect response, it first iteratively updates its context state to refocus attention on task-relevant cues, then performs minimal parameter updates to attention and readout layers. This strategy preserves generalizable representations in the sensory and attention networks, reducing catastrophic forgetting. We evaluate WiNN on an image-based extension of the Wisconsin Card Sorting Task, revealing several markers of cognitive flexibility: (i) WiNN autonomously infers underlying rules, (ii) requires fewer examples to do so than control models reliant on large-scale parameter updates, (iii) can perform context-based rule inference solely via context-state adjustments-further enhanced by slow updates of attention and readout parameters, and (iv) generalizes to unseen compositional rules through context-state updates alone. By blending fast context inference with targeted attentional guidance, WiNN achieves "sparks" of flexibility. This approach offers a path toward context-sensitive models that retain knowledge while rapidly adapting to complex, rule-based tasks.

Sushrut Thorat, Adrien Doerig, Alexander Kroner et al.

Scenes are complex, yet structured collections of parts, including objects and surfaces, that exhibit spatial and semantic relations to one another. An effective visual system therefore needs unified scene representations that relate scene parts to their location and their co-occurrence. We hypothesize that this structure can be learned self-supervised from natural experience by exploiting the temporal regularities of active vision: each fixation reveals a locally-detailed glimpse that is statistically related to the previous one via co-occurrence and saccade-conditioned spatial regularities. We instantiate this idea with Glimpse Prediction Networks (GPNs) -- recurrent models trained to predict the feature embedding of the next glimpse along human-like scanpaths over natural scenes. GPNs successfully learn co-occurrence structure and, when given relative saccade location vectors, show sensitivity to spatial arrangement. Furthermore, recurrent variants of GPNs were able to integrate information across glimpses into a unified scene representation. Notably, these scene representations align strongly with human fMRI responses during natural-scene viewing across mid/high-level visual cortex. Critically, GPNs outperform architecture- and dataset-matched controls trained with explicit semantic objectives, and match or exceed strong modern vision baselines, leaving little unique variance for those alternatives. These results establish next-glimpse prediction during active vision as a biologically plausible, self-supervised route to brain-aligned scene representations learned from natural visual experience.

Sushrut Thorat, Giacomo Aldegheri, Tim C. Kietzmann

Recurrent neural networks (RNNs) have been shown to perform better than feedforward architectures in visual object categorization tasks, especially in challenging conditions such as cluttered images. However, little is known about the exact computational role of recurrent information flow in these conditions. Here we test RNNs trained for object categorization on the hypothesis that recurrence iteratively aids object categorization via the communication of category-orthogonal auxiliary variables (the location, orientation, and scale of the object). Using diagnostic linear readouts, we find that: (a) information about auxiliary variables increases across time in all network layers, (b) this information is indeed present in the recurrent information flow, and (c) its manipulation significantly affects task performance. These observations confirm the hypothesis that category-orthogonal auxiliary variable information is conveyed through recurrent connectivity and is used to optimize category inference in cluttered environments.

Baihan Lin, Marieke Mur, Tim Kietzmann et al.

Representational similarity analysis (RSA) has been shown to be an effective framework to characterize brain-activity profiles and deep neural network activations as representational geometry by computing the pairwise distances of the response patterns as a representational dissimilarity matrix (RDM). However, how to properly analyze and visualize the representational geometry as dynamics over the time course from stimulus onset to offset is not well understood. In this work, we formulated the pipeline to understand representational dynamics with RDM movies and Procrustes-aligned Multidimensional Scaling (pMDS), and applied it to neural recording of monkey IT cortex. Our results suggest that the the multidimensional scaling alignment can genuinely capture the dynamics of the category-specific representation spaces with multiple visualization possibilities, and that object categorization may be hierarchical, multi-staged, and oscillatory (or recurrent).

Alex Hernández-García, Peter König, Tim C. Kietzmann

Deep convolutional neural networks trained for image object categorization have shown remarkable similarities with representations found across the primate ventral visual stream. Yet, artificial and biological networks still exhibit important differences. Here we investigate one such property: increasing invariance to identity-preserving image transformations found along the ventral stream. Despite theoretical evidence that invariance should emerge naturally from the optimization process, we present empirical evidence that the activations of convolutional neural networks trained for object categorization are not robust to identity-preserving image transformations commonly used in data augmentation. As a solution, we propose data augmentation invariance, an unsupervised learning objective which improves the robustness of the learned representations by promoting the similarity between the activations of augmented image samples. Our results show that this approach is a simple, yet effective and efficient (10 % increase in training time) way of increasing the invariance of the models while obtaining similar categorization performance.

Tim C Kietzmann, Courtney J Spoerer, Lynn Sörensen et al.

The human visual system is an intricate network of brain regions that enables us to recognize the world around us. Despite its abundant lateral and feedback connections, object processing is commonly viewed and studied as a feedforward process. Here, we measure and model the rapid representational dynamics across multiple stages of the human ventral stream using time-resolved brain imaging and deep learning. We observe substantial representational transformations during the first 300 ms of processing within and across ventral-stream regions. Categorical divisions emerge in sequence, cascading forward and in reverse across regions, and Granger causality analysis suggests bidirectional information flow between regions. Finally, recurrent deep neural network models clearly outperform parameter-matched feedforward models in terms of their ability to capture the multi-region cortical dynamics. Targeted virtual cooling experiments on the recurrent deep network models further substantiate the importance of their lateral and top-down connections. These results establish that recurrent models are required to understand information processing in the human ventral stream.