Having regard to the above tutorial by Edge Impulse and the fact that Brainchip is partnered with at least Tata Elxsi to drive the adoption of AKIDA technology in the field of medicine I thought newer genuine investors might find the following two papers of interest:“AbstractComputed Tomography (CT) scans play a crucial role in medical imaging, allowing neuroscientists to identify intracranial pathologies such as haemor- rhages and malignant tumours in the brain. This thesis explores the po- tential of deep learning models as an aid in intracranial pathology detection through medical imaging. By first creating a convolutional neural network model capable of identifying brain haemorrhage and then moving it onto the neuromorphic processor Akida AKD1000, it allowed the usage of Spik- ing Neural Networks and on-edge retraining capabilities. In a process called few-shot learning, the model was trained to also identify brain tumours with minimal additional samples. The research further investigated how the pa- rameters used in the edge-learning influenced classification accuracy. It was shown that the parameter selection and interaction introduced a trade-off in regard to accuracy for the haemorrhage and tumour classification models, but an optimal constellation of parameters could be extracted. These results aim to serve as a foundation for future endeavours in image analysis using neuromorphic hardware, specifically within the domain of few-shot and on- edge learning. The integration of these models in the medical field has the potential to streamline the diagnosis of intracranial pathologies, enhancing accuracy and efficiency while unloading medical professionals“AND"AbstractThe goal of this thesis is to investigate the potential of Neuromorphic Computing for detecting the neurotransmitter **A levels in the human brain. Neuromorphic Computing is a novel approach to computing that mimics the functioning of the brain, offering energy-efficient real-time processing for AI applications. In contrast to traditional computing architectures, Neuromorphic Computing offers several advantages in many applications, including parallel processing, unsupervised learning, and real-time data processing.To demonstrate the potential of Neuromorphic Computing for **A detection, the thesis will first implement traditional neural networks to analyze the feasibility of detecting **A levels and compare the actual experimentally measured **A levels. Traditional neural networks are known for their ability to model complex relationships between inputs and outputs, and for their gener- alization capability, which means they can perform well on unseen data. They have been widely used in various applications. However, traditional neural networks are computationally expensive and require a significant amount of data and power to perform their calculations. This can make them unsuitable for certain applications, such as those that require real time processing or those that operate on battery-powered devices where energy efficiency is crucial, and there is an insuffi- cient amount of data. This has led to the development of alternative computing architectures, such as Neuromorphic Computing, which includes Spiking Neural Networks, as a potential solution to overcome these limitations.Spiking Neural Networks (SNNs) are a growing trend in the field of AI and Machine Learning due to their unique approach to data processing. Unlike traditional artificial neural networks, SNNs operate in the spike domain and have the potential to be more energy-efficient and provide real-time data processing. Although much research is still needed to fully comprehend the capabilities and limitations of SNNs, it is possible to train these algorithms on the same datasets used for traditional neural networks. With their potential for energy efficiency and real time data processing, SNNs are considered a promising development for a wide range of applications.The fact that there are so many interfacing tools and systems that can interface between the neu- romorphic chip and the measuring system.The Tkinter framework is a popular and widely used graphical user interface (GUI) library in Python, that makes an ideal choice for many applications. It allows easy transmission of data between the memory unit and processing unit such as Akida Neuromorphic Processor.The system will be designed in such a way that it can be easily modified or expanded in the future if needed. The Tkinter framework provides a range of tools and functions to create a responsive and intuitive GUI, making it a perfect fit for this project. The aim is to develop a system that is not only effective in terms of functionality but also user-friendly, allowing for efficient and seamless access to previously recorded data and analyzing it before deploying to the hardware.Although DAK-3.5 is a window operating system and Akida1000 is a Linux operating system, but both can be interfaced by a python programmed system."https://www.duo.uio.no/bitstream/handle/10852/102469/1/Neuromorphic_computing_for_GABA_detection.pdfMy opinion only DYOR
Fact Finder
- Forums
- ASX - By Stock
- BRN
- Edge Impulse promotes AKIDA
Edge Impulse promotes AKIDA, page-29
-
-
- There are more pages in this discussion • 27 more messages in this thread...
You’re viewing a single post only. To view the entire thread just sign in or Join Now (FREE)
Featured News
Add BRN (ASX) to my watchlist
|
|||||
Last
18.0¢ |
Change
-0.015(7.69%) |
Mkt cap ! $353.2M |
Open | High | Low | Value | Volume |
20.0¢ | 20.5¢ | 17.8¢ | $2.552M | 13.44M |
Buyers (Bids)
No. | Vol. | Price($) |
---|---|---|
16 | 753863 | 18.0¢ |
Sellers (Offers)
Price($) | Vol. | No. |
---|---|---|
18.5¢ | 423608 | 5 |
View Market Depth
No. | Vol. | Price($) |
---|---|---|
16 | 753863 | 0.180 |
55 | 1922318 | 0.175 |
83 | 2084945 | 0.170 |
49 | 1226154 | 0.165 |
73 | 1321265 | 0.160 |
Price($) | Vol. | No. |
---|---|---|
0.185 | 423608 | 5 |
0.190 | 445356 | 6 |
0.195 | 487498 | 4 |
0.200 | 568700 | 12 |
0.205 | 707978 | 11 |
Last trade - 16.10pm 26/08/2024 (20 minute delay) ? |
Featured News
BRN (ASX) Chart |