Sensors and algorithms are two fundamental elements to construct intelligent systems. The recent progress in machine learning (ML) has produced great advancements in intelligent systems, owing to the powerful data analysis capability of ML algorithms. However, the performance of most systems is still hindered by sensing techniques that typically rely on rigid and bulky sensor devices, which cannot conform to irregularly curved and dynamic surfaces for high‐quality data acquisition. Skin‐like stretchable sensing technology with unique characteristics, such as high conformability, low modulus, and light weight, has been recently developed to solve this issue. Here, the recent progress in the fusion of emerging stretchable electronics and ML technology, for bioelectrical signal recognition, tactile perception, and multimodal integration is summarized, and the challenges and future developments are further discussed. These efforts aim to accelerate various perception and reasoning tasks for advanced intelligent applications, such as human–machine interfaces, healthcare, and robotics.

Ultrafast artificial skin enables unprecedented tactile internet applications in prosthetics, robotics, and human–machine interactions. However, current artificial skin systems that rely on front‐end interface electronics typically perform redundant data transfer and analogue‐to‐digital conversions for decision‐making, causing long latency (milliseconds). Here, a near‐sensor analogue computing system based on a flexible memristor array for artificial skin applications is reported. This system, which seamlessly integrates a tactile sensor array with a flexible hafnium oxide memristor array, can simultaneously sense and compute raw multiple analogue pressure signals without interface electronics. As a proof‐of‐concept, the system is used for real‐time noise reduction and edge detection of tactile stimuli. One sensing–computing operation of this system takes about 400 ns and consumes on average 1000 times less power than a conventional interface electronic system. The results demonstrate that near‐sensor analogue computing offers an ultrafast and energy‐efficient route to large‐scale artificial skin systems.

Two-dimensional metal−organic frameworks (2D-MOFs) and their derivatives are promising for catalysis, energy storage, gas separation, etc. due to their unique microstructure and physicochemical properties. Many efforts have been devoted to fabricating 2D-MOFs with challenges remaining in yield and fine control of their thickness and lateral size. Here a versatile strategy has been used involving epitaxial, anisotropic, and confined growth of CoNi-MOF-71 nanosheet arrays, giving rise to excellent quantity and controllability of the 2D-MOFs. Electromagnetic (EM) wave absorption performance has been investigated for the resultant 2D Co/Ni/C derivatives. Compared with the bulk counterpart, significantly increased surface area, conductivity, and shape anisotropy for the 2D derivatives result in enhanced interfacial polarization, conductive loss, and magnetic resonance. As such, optimum EM wave absorption of minimum reflection loss RL min = −49.8 dB and an ultrawide effective adsorption bandwidth EAB = 7.6 GHz can be achieved at a thickness of 2.6 mm. This work not only sheds light on the performance enhancement for 2D absorbers via synergistic effects of multiple attenuation mechanisms but also provides an effective fabrication route of ultrathin MOFs with high yield and uniform size for extended applications in catalysis, electrochemistry, and optoelectronics fields.