TY - JOUR TI - Unsupervised learning of haptic material properties AU - Metzger, Anna AU - Toscani, Matteo A2 - Sharpee, Tatyana O A2 - Baker, Chris I A2 - Ahissar, Ehud A2 - Bensmaia, Sliman J VL - 11 PY - 2022 DA - 2022/02/23 SP - e64876 C1 - eLife 2022;11:e64876 DO - 10.7554/eLife.64876 UR - https://doi.org/10.7554/eLife.64876 AB - When touching the surface of an object, its spatial structure translates into a vibration on the skin. The perceptual system evolved to translate this pattern into a representation that allows to distinguish between different materials. Here, we show that perceptual haptic representation of materials emerges from efficient encoding of vibratory patterns elicited by the interaction with materials. We trained a deep neural network with unsupervised learning (Autoencoder) to reconstruct vibratory patterns elicited by human haptic exploration of different materials. The learned compressed representation (i.e., latent space) allows for classification of material categories (i.e., plastic, stone, wood, fabric, leather/wool, paper, and metal). More importantly, classification performance is higher with perceptual category labels as compared to ground truth ones, and distances between categories in the latent space resemble perceptual distances, suggesting a similar coding. Crucially, the classification performance and the similarity between the perceptual and the latent space decrease with decreasing compression level. We could further show that the temporal tuning of the emergent latent dimensions is similar to properties of human tactile receptors. KW - touch KW - natural textures KW - materials KW - unsupervised deep learning KW - haptic perception KW - efficient coding JF - eLife SN - 2050-084X PB - eLife Sciences Publications, Ltd ER -