{"slug": "meta-learning-as-a-principle-for-human-like-visual-representations", "title": "Meta-learning as a principle for human-like visual representations", "summary": "Researchers at arXiv propose that meta-learning, or learning to learn, may explain why human visual representations are more flexible than those of pretrained neural networks. By training a sequence model on thousands of tasks without human data, they found meta-learned representations better predict human similarity judgments, semantic rule learning, and high-level visual cortex activity. The findings suggest human visual flexibility arises from the need to learn new semantic relationships quickly.", "body_md": "arXiv:2606.28399v1 Announce Type: new\nAbstract: The structure of human visual representations underpins our capacity for adaptive behaviour. While pretrained neural networks model human visual representations with unprecedented success, a large discrepancy remains. We propose one reason: these networks optimise a single fixed objective, whereas human representations must support open-ended tasks. We hypothesise this flexibility arises from meta-learning (learning to learn), a pressure shaping representations to acquire new tasks from few observations. To test this, we train a sequence model, without any supervision from human data, across thousands of semantically rich tasks mapping images to high-level concepts. Compared to their pretrained base encoders, meta-learned representations better predict human similarity judgements, semantic rule learning, and high-level visual cortex. Behavioural gains depend on disentangled, high-level task distributions, while brain alignment is driven primarily by the learning-to-learn pressure. Our results suggest the flexibility of human visual representations reflects the functional demand to learn new semantic relationships on the fly.", "url": "https://wpnews.pro/news/meta-learning-as-a-principle-for-human-like-visual-representations", "canonical_source": "https://arxiv.org/abs/2606.28399", "published_at": "2026-06-30 04:00:00+00:00", "updated_at": "2026-06-30 04:25:14.248194+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "computer-vision", "artificial-intelligence"], "entities": ["arXiv"], "alternates": {"html": "https://wpnews.pro/news/meta-learning-as-a-principle-for-human-like-visual-representations", "markdown": "https://wpnews.pro/news/meta-learning-as-a-principle-for-human-like-visual-representations.md", "text": "https://wpnews.pro/news/meta-learning-as-a-principle-for-human-like-visual-representations.txt", "jsonld": "https://wpnews.pro/news/meta-learning-as-a-principle-for-human-like-visual-representations.jsonld"}}