硬體加速器

These stimuli-switchable nanoparticles coated with the cleavable outer polymer coatingmultifunctional peptides may afford a new platform for anticancer drugmiR. These nanoparticles possess characteristics of environmental response, active targeting,gene/chemo combinatorial therapeutics, thus providing spatiotemporal control of posttranｓｃｒｉｐｔional gene regulation, smart nuclear/mitochondrial localization,simultaneous inhibition of multiple progression pathways of tumor cells for enhancing antitumor efficacysafety of cancer therapy.

Inorganic porous nanofibers with surfaceinterface defects are prepared through humidity-controlled electrospinninghigh-temperature annealing technology. Under the irradiation of light sources of different wavelengths (380~780 nm), the bound electrons stored in the valence band can be excited to the conduction band to form free electrons on the surface of the material, generating different intensities of microcurrents, light sensitivitymicrocurrent changes. Because the "inorganic nanofiber" technology has high uniquenesshigh product compatibility, it can be applied to a wide range of markets.

Inorganic porous nanofibers with surfaceinterface defects are prepared through humidity-controlled electrospinninghigh-temperature annealing technology. Under the irradiation of light sources of different wavelengths (380~780 nm), the bound electrons stored in the valence band can be excited to the conduction band to form free electrons on the surface of the material, generating different intensities of microcurrents, light sensitivitymicrocurrent changes. Because the "inorganic nanofiber" technology has high uniquenesshigh product compatibility, it can be applied to a wide range of markets.

Low-power deep learning accelerator integrates neural network design / training, model compressionaccelerator design. It uses a small amount of computationmemory footprint to realize high performance on the edge device. The image semantic segmentation technology can reach 80 frames per second (resolution:1024*2048) to meet real-time requirements for autonomous driving.

"We will demonstrate the following three technical achievements of our joint project: 1. Deployment of HarDNet on GPU (power consumption: 200 Watts) 2. Deployment of HarDNet on FPGA (power consumption: several tens of Watts) [winning 2nd place in the FPGA track, LPCVC 2020] 3. Deployment of HarDNet on lightweight edge devices such as Raspberry Pi (power consumption: single-digit, 10 Watts) [winning 3rd place in the DSP track4th place in the CPU track, LPCVC 2020]"

"1. Use PE Cluster to make the calculation reconfigurable,can be modularized into 36X PEs, supporting up to 2160PEs 2. It can be configured as an independent IP with high computing throughputlow power consumption. The computing performance can reach 864 GOPS@200MHz when 2160PEs are employed."

Dynamic vision sensors have been investigated to report motion-only images for moving object recognition. Less but essential information helps post-process recognition algorithm reduces computationimproves accuracy. Implement low powerlow latency deep Learning chip based on neuromorphic Intelligence. The neuromorphic obstacle detection algorithm integrates visualproprioceptive signals. The algorithm is characterized by its efficiencylow power consumption. We possess the next-generation in-memory computing AI chipsnext-generation UAV key softwarehardware technology