No abstract

No abstract

Compact inverse‐opal structures are constructed using non‐aggregated TiO2 nanoparticles in a three‐dimensional colloidal array template as the photoelectrode of a dye‐sensitized solar cell. Organic‐layer‐coated titania nanoparticles show an enhanced infiltration and a compact packing within the 3D array. Subsequent thermal decomposition to remove the organic template followed by impregnation with N‐719 dye results in excellent inverse‐opal photoelectrodes with a photo‐conversion efficiency as high as 3.47% under air mass 1.5 illumination. This colloidal‐template approach using non‐aggregated nanoparticles provides a simple and versatile way to produce efficient inverse‐opal structures with the ability to control parameters such as cavity diameter and film thickness.

Progress in deep learning has spawned great successes in many engineering applications. As a prime example, convolutional neural networks, a type of feedforward neural networks, are now approaching -and sometimes even surpassing -human accuracy on a variety of visual recognition tasks. Here, however, we show that these neural networks and their recent extensions struggle in recognition tasks where co-dependent visual features must be detected over long spatial ranges. We introduce a visual challenge, Pathfinder, and describe a novel recurrent neural network architecture called the horizontal gated recurrent unit (hGRU) to learn intrinsic horizontal connections -both within and across feature columns. We demonstrate that a single hGRU layer matches or outperforms all tested feedforward hierarchical baselines including state-of-the-art architectures with orders of magnitude more parameters.

The advent of deep learning has recently led to great successes in various engineering applications. As a prime example, convolutional neural networks, a type of feedforward neural network, now approach human accuracy on visual recognition tasks like image classification and face recognition. However, here we will show that feedforward neural networks struggle to learn abstract visual relations that are effortlessly recognized by non-human primates, birds, rodents and even insects. We systematically study the ability of feedforward neural networks to learn to recognize a variety of visual relations and demonstrate that same-different visual relations pose a particular strain on these networks. Networks fail to learn same-different visual relations when stimulus variability makes rote memorization difficult. Further, we show that learning same-different problems becomes trivial for a feedforward network that is fed with perceptually grouped stimuli. This demonstration and the comparative success of biological vision in learning visual relations suggests that feedback mechanisms such as attention, working memory and perceptual grouping may be the key components underlying human-level abstract visual reasoning.