Asia Times: Do Japanese manufacturers use ChatGPT?
Chat GPT: Some Japanese manufacturers may use ChatGPT or other similar language models for various applications…but which Japanese manufacturers currently use ChatGPT or other similar language models? We do not have access to certain information about whether…
Asia Times: what about panasonic?
Chat GPT: I have no access to information about whether Panasonic specifically uses ChatGPT or other similar language models. But it is possible…
Asia Times: how about this?
Nikkei Asia: Panasonic Unit Introduces ChatGPT-Style AI to Boost Productivity (03/08/2023) Expects productivity to improve.
Nikkei learned that Panasonic Connect has enabled all 12,500 employees in Japan to use AI as an “assistant” for tasks such as drafting documents.
Through a partnership with Microsoft, the company has developed an AI assistant that answers employee questions, using technology from the US company OpenAI, which developed ChatGPT, a conversational AI.
The company uses an AI system to create statistical data in a format that is easy to handle with spreadsheet software, create document templates, and solicit ideas for how to proceed with meetings.
To prevent information leaks, the system can only be used within Panasonic Connect’s internal network. To mitigate such risks, Panasonic Connect has agreed with Microsoft not to use content for secondary purposes such as AI learning. Additionally, the company warns employees not to enter personal or confidential information.
Chat GPT: Thanks for the update! According to an article in Nikkei Asia, Panasonic Connect, a system development company under Panasonic Holdings, has actually introduced an AI assistant that utilizes the technology of OpenAI, the developer of ChatGPT, to improve productivity.
be careful
Shortcut seekers beware. The previous conversation shows the verbose ChatGPT that even when prompted by the name Panasonic, he failed to notice an article published five weeks ago on a well-known English-language business website. Google found the article in less than a second.
And from this article, Elon Musk, Steve Wozniak, and more than 1,000 other stakeholders called on all artificial intelligence labs on March 14 to “immediately suspend training of more powerful AI systems for at least six months.” Before issuing the “call” to “stop”, I found the following: “More than GPT-4” because of “serious risks to society and humanity” – Panasonic had already started implementing a low-risk in-house version of the technology.
So we’re caught up in the hoopla over ChatGPT, the most widely published information about AI in Japan, but in the process distracted from more important applications across different industries. . For example:
- Pharmaceuticals: Astellas Pharma has created a cell drug discovery platform that integrates humans, AI and robotics. Successful cases claim to reduce drug candidate acquisition time by approximately 70%. Currently, it is being used in a joint research project with Kyoto University iPS Cell Research Institute to promote the use of differentiated cells and tissues derived from human induced pluripotent stem cells (iPS cells) and create innovative medical solutions. “
- Regenerative medicine: Canon plans to acquire Kyoto Manufacturing’s high-speed cell culture system technology (scheduled for completion in May) and apply deep learning neural networks for image processing to regenerative medicine.
- Factory worker support: Hitachi has developed a “real-time work deviation detection” system based on deep learning that mitigates inefficiencies caused by human-machine interaction in highly automated factories. The company also uses neural networks to improve fault detection in complex industrial and infrastructure equipment, systems, and networks. Once primarily an industrial hardware conglomerate, Hitachi now applies digital technology to everything it does.
- Supply chain logistics: Hitachi has also developed algorithms to maximize the efficiency of complex supply chain networks that include multiple factories, warehouses and stores connected by land, sea and air. This includes production scheduling, inventory management and maximizing delivery route efficiency.
- quality management: NEC uses machine learning to standardize and speed up product inspection, save time previously spent on visual inspection, and improve accuracy through objective data analysis. In addition, we automatically analyze sensor data such as temperature, vibration, pressure, voltage, and flow rate in real time to monitor power generation equipment. This “allows us to detect abnormalities in the early symptom stages, including subtle abnormalities that even the laboratory specialist may not be aware of.”
- Industrial cyber security: Fujitsu offers services ranging from evaluation of manufacturers’ operational technology, design and implementation of cyber security systems, continuous monitoring, incident investigations, and system upgrades. They are based on data analysis and Fujitsu’s own experience as a manufacturer of computing and communications equipment.
- Embedded system: Semiconductor manufacturer Renesas is putting artificial intelligence into its embedded systems (e-AI) to perform inference on its MCUs, MPUs, and AI accelerators. This enables real-time processing without the network delays inherent in cloud computing. Applications include factory automation monitoring (for example, to combat abnormal vibrations), tuning of automated system devices, motor control, or other failure prediction.
- Semiconductor metrology: Hitachi applies deep learning to scanning electron microscopy (CD-SEM) to more accurately measure high-aspect-ratio hole defects in post-etch 3D semiconductor devices (such as NAND flash memory), thereby Improve process control. Hitachi also makes etching equipment.
The list goes on and on, covering healthcare, traffic control, waste management, wind turbine performance, and anything else that requires processing vast amounts of data. This all goes well beyond ChatGPT, but that doesn’t mean it might not steal your job.
definition
“The easiest way to think about artificial intelligence, machine learning, neural networks that use algorithms to mimic the human brain, and deep learning is to think of them like Russian nesting dolls,” IBM said. doing. Each is essentially a component of the previous period. “
In other words, “Machine learning is a subfield of artificial intelligence. Deep learning is a subfield of machine learning, and neural networks form the backbone of deep learning algorithms.”
IC design firm Arm said:
AI inference is enabled by an “inference engine” that applies logical rules to a knowledge base to evaluate and analyze new information. The machine learning process has two phases.
The first is the training phase, where intelligence is developed by recording, storing, and labeling information. For example, if you are training a machine to identify cars, the machine learning algorithm is fed many images of different cars that the machine can later refer to.
The second is the inference phase, where the machine uses the intelligence collected and stored in phase 1 to make sense of new data. During this phase, the machine can use inference to identify and classify new images as “cars” even though they have never seen them before. In more complex scenarios, this inference learning can be used to enhance human decision making.
Similarly, if you feed news articles into ChatGPT, they will be cited immediately. But it doesn’t run an industrial economy.
Follow this writer on Twitter: @ScottFo83517667
