Industrial AI & Machine Lear1ing
 
 
 
 
Micropower intelligence for edge devices

NARAYAN SRINIVASA AND GOPAL RAGHAVAN, ETA COMPUTE

The world is moving toward a smart and distributed computing model of interacting devices. Intelligence in these devices will be driven by machine learning algorithms. Yet, extending machine learning to the edge is not without its challenges. The following discusses the landscape of these challenges and then describe how neuromorphic ? brain-inspired ? computing will enable a wide range of intelligent applications that address these challenges. 
READ MORE
 
 
 
FEATURE
 
img_185X240
In a neural network graph, sparsity refers to neurons that contain a zero value or no connection to adjacent neurons. This is an inherent characteristic of the hidden matrices that exist between the input and output layers of a deep neural network, as a given input typically activates fewer and fewer neurons as data passes through the graph. The fewer connections in the neural network matrix, the higher the sparsity.
 
 
NEWS
 
img_185X240
Flex Logix has launched their new NMAX Neural Inferencing Engine, delivering 1 to >100 TOPS of neural inferencing capacity in a modular, scalable architecture requiring a fraction of the DRAM bandwidth of existing neural inferencing solutions.
 
 
 
 

FEATURE

 
img_185X240
Industry 4.0 is characterized by applying cloud and cognitive computing to current automated and computerized industrial systems resulting in the ability to create smart factories that monitor physical processes, identify issues or optimizations, and perform iterative refinement or proactive maintenance and updates.  A recent study was released by Emory University and Presenso called ?The Future of IIoT Predictive Maintenance.? The study is focused on predictive maintenance current state, implemention, resulting impact, and future needs identified within smart factories.
 
Socionext
 
 
 
BLOG
 
img_185X240
With Moore?s law coming to an end and the growing volume of data that will require to be processed to drive the next wave of AI applications, CPUs are no longer able to keep up with the compute requirements. As neural networks evolve and get more efficient along with changes to datasets, workloads and algorithms, the on-chip hardware accelerators needs to be programmable and flexible. Embedding a programmable FPGA fabric inside the SoC with Speedcore eFPGA is an ideal solution for next-generation AI applications.
 
 
BLOG
 
img_185X240
Intel recently unveiled its family of Vision Accelerator Design Products aimed at artificial intelligence (AI) inference and analytics performance on Edge devices, where data originate and are acted upon. The products come in two forms: one that features an array of Intel Movidius vision processors and one built on the company?s Arria 10 FPGA.
 
 
 
 
FEATURE
 
img_185X240
About six years ago, there was a major shock in a somewhat obscure corner of the computing world when a team from the University of Toronto won the Imagenet Challenge using a convolutional neural network that was trained, rather than designed, to recognize images. That team, and others, went on to not only beat out the very best detection algorithms but to outperform humans in many image classification tasks. Now, only a few years later, it seems that deep neural networks are inescapable.
 
 
PODCAST
 
img_185X240
Work on artificial intelligence (AI) is taking place in all corners of the globe. In fact, a recent event was held in China to further the advancement of AI as it relates to heterogeneous computing.
 
 
 
 
BLOG
 
img_185X240
MediaTek recently announced the launch of the Helio P70 system-on-chip (SoC), with an enhanced AI engine combined with CPU and GPU upgrades for more powerful AI processing. Helio P70 also comes with upgraded imaging and camera support, a gaming performance boost and advanced connectivity features.
 
 
BLOG
 
img_185X240
Autonomous vehicles are coming. I?m sure of it. If you ask me when, I?m afraid I can?t give a definitive answer. Actual mass deployment is a moving target and it seems like we?ve been in beta mode for quite a few years.
 
 
 
 
NEWS
 
img_185X240
Esperanto Technologies announced that it has received $58 million from several strategic and venture capital investors in its Series B funding round, bringing the total investment in Esperanto to $63 million.
 
 
NEWS
 
img_185X240
AAEON has introduced the BOXER-6841M, a box PC designed for edge AI and machine vision applications. The controller comes in six different models, with four AI versions featuring PCIe(x16) slots for the installation of Nvidia GPUs, and two machine vision versions including a pair of PCIe(x8) slots for frame grabber cards.
 
 
 
 
NEWS
 
img_185X240
Renesas Electronics? new RZ/A2M microprocessor (MPU) will extend the use of (e-AI) solutions to high-end applications, delivering 10 times the image processing performance of its predecessor, the RZ/A1.
 
 
NEWS
 
img_185X240
FogHorn released its Lightning 2.0 software with additions establishing new industry benchmarks for edge-based machine learning (EdgeML), massively scalable edge deployment support, zero-touch sensor configuration, out-of-the-box multi-cloud integration, and next generation OT tools.
 
 
 
 
 
 
Sponsored by: QuickLogic, Samsung
Date: December 11, 2:00 p.m. ET
Register Now
 
 
 
 
Facebook
 
Twitter
 
Linkedin