@Diogenese or anyone else more techy.....opinion or education pls
The BRN patent below was one filed in 2019 and whilst we all know of SNN I see references to SCNN as a spiking convolutional neural network which we've also heard of.
I noticed the acronym used within some NetApp documentation in relation to AI, NVDA examples etc. (some snips & links below) and mused whether their use of the acronym is similar. They call it Spatial Convolutional Neural Network and relates to autonomous driving and other uses but will stick to AD for this purpose. They do reference it across to GPUs as well, so is it something that is purely GPU driven by NetApp files, embedded or something else.
My question is:
Within our patent I also see references to the spatial nature of the spikes and presume NetApp's use of the term is purely around the "spatial" effect within CNN but given we know we can convert CNN to SNN?
Are these 2 distinctly separately terms / uses or could there be an overlap as we know the industry all uses various acronyms to suit their own discussions, products but are essentially one and the same or similar?
Are we able to be integrated cloud side?
Disclosed herein are system, method, and computer program product embodiments for an improved spiking neural network (SNN) configured to learn and perform unsupervised extraction of features from an input stream. An embodiment operates by receiving a set of spike bits corresponding to a set...
patents.google.com
But conventional SNNs can suffer from several technological problems. First, conventional SNNs are unable to switch between convolution and fully connected operation. For example, a conventional SNN may be configured at design time to use a fully-connected feedforward architecture to learn features and classify data. Embodiments herein (e.g., the neuromorphic integrated circuit) solve this technological problem by combining the features of a CNN and a SNN into a spiking convolutional neural network (SCNN) that can be configured to switch between a convolution operation or a fully-connected neural network function. The SCNN may also reduce the number of synapse weights for each neuron. This can also allow the SCNN to be deeper (e.g., have more layers) than a conventional SNN with fewer synapse weights for each neuron. Embodiments herein further improve the convolution operation by using a winner-take-all (WTA) approach for each neuron acting as a filter at particular position of the input space. This can improve the selectivity and invariance of the network. In other words, this can improve the accuracy of an inference operation.
- In some embodiments, an input to a SCNN is derived from an audio stream. An Analog to Digital (A/D) converter can convert the audio stream to digital data. The A/D converter can output the digital data in the form of Pulse Code Modulation (PCM) data. A data to spike converter can convert the digital data to a series of spatially and temporally distributed spikes representing the spectrum of the audio stream.
- [0052]
In some embodiments, an input to a SCNN is derived from a video stream. The A/D converter can convert the video stream to digital data. For example, the A/D converter can convert the video stream to pixel information in which the intensity of each pixel is expressed as a digital value. A digital camera can provide such pixel information. For example, the digital camera can provide pixel information in the form of three 8-bit values for red, green and blue pixels. The pixel information can be captured and stored in memory. The data to spike converter can convert the pixel information to spatially and temporally distributed spikes by means of sensory neurons that simulate the actions of the human visual tract.
In this architecture, the focus is on the most computationally intensive part of the AI or machine learning (ML) distributed training process of lane detection.
docs.netapp.com
The elements used in this solution are:
- Azure Kubernetes Service (AKS)
- Azure Compute SKUs with NVIDIA GPUs
- Azure NetApp Files
- RUN: AI
- NetApp Trident
In this architecture, the focus is on the most computationally intensive part of the AI or machine learning (ML) distributed training process of lane detection. Lane detection is one of the most important tasks in autonomous driving, which helps to guide vehicles by localization of the lane markings. Static components like lane markings guide the vehicle to drive on the highway interactively and safely.
Convolutional Neural Network (CNN)-based approaches have pushed scene understanding and segmentation to a new level. Although it doesn’t perform well for objects with long structures and regions that could be occluded (for example, poles, shade on the lane, and so on).
Spatial Convolutional Neural Network (SCNN) generalizes the CNN to a rich spatial level. It allows information propagation between neurons in the same layer, which makes it best suited for structured objects such as lanes, poles, or truck with occlusions. This compatibility is because the spatial information can be reinforced, and it preserves smoothness and continuity.
Thousands of scene images need to be injected in the system to allow the model learn and distinguish the various components in the dataset. These images include weather, daytime or nighttime, multilane highway roads, and other traffic conditions.
For training, there is a need for good quality and quantity of data. Single GPU or multiple GPUs can take days to weeks to complete the training. Data-distributed training can speed up the process by using multiple and multinode GPUs. Horovod is one such framework that grants distributed training but reading data across clusters of GPUs could act as a hindrance. Azure NetApp Files provides ultrafast, high throughput and sustained low latency to provide scale-out/scale-up capabilities so that GPUs are leveraged to the best of their computational capacity.
Our experiments verified that all the GPUs across the cluster are used more than 96% on average for training the lane detection using SCNN.
NetApp, Inc. is an American hybrid cloud data services and data management company headquartered in San Jose, California. It has ranked in the Fortune 500 from 2012–2021. Founded in 1992 with an IPO in 1995, NetApp offers cloud data services for management of applications and data both online and physically.
NetApp® AI solutions drive your AI success in automotive. Be a leader and innovator in the AI automotive industry with data-driven software applications from NetApp.
www.netapp.com
- HOME
- ARTIFICIAL INTELLIGENCE
- AI IN AUTOMOTIVE
AI in the automotive industry: Innovation turbocharged
AI is driving the future—and present—of the automotive industry, leaving the past in the dust. With the right AI infrastructure, you can stay ahead of the competition and meet ever-evolving customer demands.