Years in the making: 304 papers cited in a huge effort to characterise this emerging field that we hold dearly. Read this paper to find out what we are doing, why and how, and why we think that ANNs are a central tool for understand brain computations. #neuroconnectionism.

RT @TimKietzmann: Exciting new preprint from the lab: “Adopting a human developmental visual diet yields robust, shape-based AI vision”. A….

#AI and #computervision folks: this will be interesting to you! . Robust visual inference beyond scale, but achieved by taking inspiration from how infant vision develops. Shown to work across many architectures and comes with a neat preprocessing pipeline that you can use.

We are incredibly excited about this because DVD may offer a resource-efficient path towards safer, more human-like AI vision — and suggests that biology, neuroscience, and psychology have much to offer in guiding the next generation of artificial intelligence. #NeuroAI /fin.

In summary, DVD-training yields models that rely on a fundamentally different feature set, shifting from distributed local textures to integrative, shape-based features as the foundation for their decisions. 9/.

Result 4: How about adversarial robustness? DVD-trained models also showed greater resilience to all black- and white-box attacks tested, performing 3–5 times better than baselines under high-strength perturbations. 8/

Result 3: DVD-trained models exhibit more human-like robustness to Gaussian blur compared to baselines, plus an overall improved robustness to all image perturbations tested. 7/

Result 2: DVD-training enabled abstract shape recognition in cases where AI frontier models, despite being explicitly prompted, fail spectacularly. t-SNE nicely visualises the fundamentally different approach of DVD-trained models. 6/

Layerwise relevance propagation revealed that DVD-training resulted in a different recognition strategy than baseline controls: DVD-training puts emphasis on large parts of the objects, rather than highly localised or highly distributed features. 5/

Result 1: DVD training massively improves shape-reliance in ANNs. We report a new state of the art, reaching human-level shape-bias (even though the model uses orders of magnitude less data and parameters). This was true for all datasets and architectures tested 4/

We then test the resulting DNNs across a range of conditions, each selected because they are challenging to AI: (i) shape-texture bias, (ii) recognising abstract shapes embedded in complex backgrounds, (iii) robustness to image perturbations, and (iv) adversarial robustness, 3/

The core idea: instead of high-fidelity training from the get-go (the gold standard), we simulate the visual development from newborns to 25 years of age by synthesising decades of developmental vision research into an AI preprocessing pipeline (Developmental Visual Diet, DVD) 2/

Exciting new preprint from the lab: “Adopting a human developmental visual diet yields robust, shape-based AI vision”. A most wonderful case where brain inspiration massively improved AI solutions. Work with @lu_zejin @martisamuser and Radoslaw Cichy.

RT @NatureHumBehav: In this study, Lu et al. introduce All-Topographic Neural Networks (All-TNN) as a parsimonious model of the human visua….

RT @aipulserx: How can we build neural networks that develop the same topographic organization as primate visual cortex and better predict….

RT @TimKietzmann: Introducing All-TNNs: Topographic deep neural networks that exhibit ventral-stream-like feature tuning and a better match….

Introducing All-TNNs: Topographic deep neural networks that exhibit ventral-stream-like feature tuning and a better match to human behaviour than the gold standard. Now out in Nature Human Behaviour. 👇.

RT @dyamins: Come to our CCN workshop! Blending iophysical constraints and neural networks. Topographical ANNs + and much more. @meen….

RT @HannesMehrer: Announcement: Workshop at #CCN2025.🧠 Modeling the Physical Brain: Spatial Organization & Biophysical Constraints .🗓️ Mond….

RT @JohnHolbein1: Timeless advice

RT @hsteven9: I am so happy—this is the first 1st author paper I have written, since the cancer diagnosis of my late wife seven years ago.….