Since YOLOv7 was proposed on July 7, 2022, fast has once again  become one of the trends in AI research.

YOLOv7 has been widely echoed since its introduction in July 2022. It received the most stars on the AI research Github of the month. Not only that, it also won the fourth place on the twitter AI research list of the month. Research based on YOLOv7 has also sprung up like mushrooms after the rain, and has been cited more than 10 times in just two months. We believe that from now on, various state-of-the-art computer vision systems will use YOLOv7 as the first step for their core systems, including OSTA autonomous driving perception technology, and multi-object tracking, which are popular technologies.

Research based on the twitter AI research list of the month.

  參考資料

When the energy consumption of AI products can be significantly reduced, they can create benefits and be widely used. Therefore, the German government raise a challenge to design and test the energy-saving microelectronic chips which can execute powerful algorithms. The AI system must successfully identify arrhythmia cases in ECG data with at least 90% accuracy in almost real-time and consume minimal energy.

Although AI has great potential for industrial innovation and field applications, the use and training of AI is energy-intensive. Only when the energy consumption of microelectronic products using AI can be reduced, AI can create benefits and be widely used in different applications.

Therefore, the German Federal Ministry of Education and Research (BMBF) launches a pilot competition "Energy-saving AI System" to select four best teams in different technology categories. Each team will receive 1 million euros to jointly develop innovative products with industry partners. The challenge of this competition requires them to design and test energy-saving microelectronic chips which can execute powerful algorithms. The AI system must successfully identify arrhythmia cases in ECG data with at least 90% accuracy in almost real-time and consume minimal energy. The 16,000 pieces of data studied in this competition were provided by the Charité Telemedicine Center in Berlin in accordance with the General Data Protection Regulation (GDPR), with half the data of patients and half of healthy people.

For example, the project "Lo3-ML" (Low-Power Low-Memory Low-Cost ECG signal analysis using ML algorithms) who won the ASIC 130nm technology category, the team develop the AI chip which includes Resistive RAM (RRAM) and can be activated ultra-low-power (Ultra-Low-Power) mode when reading and writing. Compared to the "Always-On" system, this AI system will enter a "sleep" mode to save up to 95% of power usage; and even the AI system "sleeps", data collection can still be carried out, and the AI system can be quickly activated again in a short time.

Reference

A joint research group led by Genki Kanda at the RIKEN Center for Biosystems Dynamics Research (BDR) has developed a robotic artificial intelligence (AI) system for autonomously determining the optimal conditions for growing replacement retina layers necessary for vision. The AI controlled a trial and error process spanning 200 million possible conditions that succeeded in improving cell culture recipes used in regenerative medicine. This achievement, published in the scientific journal eLife on June 28, is just one example of how the automated design and execution of scientific experiments can increase the efficiency and speed of life science research in general.

A joint research group led by Genki Kanda at the RIKEN Center for Biosystems Dynamics Research (BDR) has developed a robotic artificial intelligence (AI) system for autonomously determining the optimal conditions for growing replacement retina layers necessary for vision.The system has successfully improved the cell culture methodology in regenerative medicine by treating 200 million possible conditions by AI.The results were published in the international top-notch journal eLife on June 28 to demonstrate the efficiency and speed with which scientific experiments are designed and executed automatically to optimize overall life science research.

Research in regenerative medicine often requires numerous experiments that are both time-consuming and labor-intensive. In particular, creating specific tissue from stem cells—a process called induced cell differentiation—involves months of work, and the degree of success depends on a wide range of variables. Finding the optimal type, dose, and timing of reagents, as well as optimal physical variables such as pipette strength, cell transfer time, and temperature is difficult and requires an enormous amount trial and error. As Kanda explains, “because minute differences in physical conditions have a significant impact on quality, and because inducing cell differentiation takes weeks to months of time in culture, the impact of a tiny difference in timing on day 3 might not be detected for several months.”

To make this process more efficient and practical, the BDR team set out to develop an autonomous experimental system that can determine the optimal conditions and grow functional retinal pigment layers from stem cells. Retinal pigment epithelium (RPE) cells were chosen because degeneration of these cells is a common age-related disorder that leaves people unable to see. Equally important, transplanted RPE retinal layers have already been shown to have some clinical success.

For autonomous experiments to be successful, the robot must repeatedly produce the same series of precise movements and manipulations, and the AI must be able to evaluate the results and formulate the next experiment. The new system accomplishes these goals using a general-purpose humanoid robot – named Maholo – capable of highly precise life science experimental behavior. Maholo is controlled by AI software that uses a newly designed optimization algorithm to determine which parameters should be changed, and how they should be changed, to improve differentiation efficiency in the next round of experiments.

Researchers input the necessary protocols for generating RPE cells from stem cells into Maholo. While RPE cells were successfully generated in all experiments, efficiency was only 50%. Thus, for every 100 stem cells, only about 50 became RPE cells. After establishing this baseline, the AI initiated the optimization process to determine the best conditions among all chemical and physical parameters. What would have taken humans over two and a half years to complete only took the robotic AI system 185 days, and resulted in a 90% rate of differentiation efficiency. Practically, these cells displayed many of the typical biological markers that would make them suitable for transplant into an eye with a damaged RPE cell layer.

The success of the new system goes beyond the immediate results. “We chose to differentiate RPE cells from stem cells as a model,” says Kanda, “but in principle, combining a precision robot with the optimization algorithms will enable autonomous trial and error experiments in many areas of life science.”

However, the researchers emphasize that the goal of the study is not to replace human lab workers with robots. “Using robots and AI for carrying out experiments will be of great interest to the public,” says Kanda. “However, it is a mistake to see them as replacements. Our vision is for people to do what they are good at, which is being creative. We can use robots and AI for the trial-and-error parts of experiments that require repeatable precision and take up a lot of time, but do not require thinking.”

Reference