The global market for large screen televisions is on a surge. According to global market research firm Omdia, global shipments of TVs with displays over 75-inches are expected to increase by 17% compared to 2019 and 8K TVs are set to increase by 110% this year as well.

Given the market demands, Samsung is doubling down on its efforts to give consumers large screen TVs that not only offer the best picture quality but also the best sound experiences.

At the heart of that is Samsung’s AI Quantum Processor.

The AI Quantum Processor is a high-performing chip developed using Samsung’s proprietary technologies that can process complex algorithms quickly using machine learning-based upscaling. That gives consumers the ability to stream 8K content in real-time paired with dynamic, location-based acoustics.

Samsung is peeling back the secrets of the AI Quantum Processor to share on how it brings these experiences together to get better resolution, better sound and better picture integrity.

One of the leading questions consumers continue to ask about large screen TVs is how to watch ultra HD content in 8K resolution given that it isn’t widely available yet. That’s where Samsung’s AI upscaling technology comes in.

Today, the technology transforms not only 4K content into 8K, but it also works for lower-resolution SD, HD and FHD-quality content as well. The AI Quantum Processor 8K combines the advantages of existing machine learning capabilities with new deep learning technologies to analyze and deliver content at some of the most granular levels possible.

This hybrid approach helps to remove unnecessary noise and creates life-like textures and smooth edges on upscaled 8K content that only Samsung can deliver. It also adjusts content brightness and darkness levels according to the light and living room conditions the display is set up in.

AI Quantum Sound for the Most Suitable Audio Experiences

Adding a truly effective audio experience to high-quality picture quality serves to bring about an even deeper sense of immersion to viewers. Samsung’s AI Quantum Sound, bolstered by artificial intelligence, provides a listening experience similar to that of a movie theater right in your living room.

Samsung’s new innovative sound technology Object Tracking Sound+ follows movement on-screen to match the direction of the sound to the action. The technology recognized and analyzes the recorded audio synced to the content in real-time and evenly distributes the audio tracks to the six speakers embedded in the TV.

And due in part to the Active Voice Amplifier (AVA), users will never miss a word of dialogue, regardless of what is happening around the TV. The feature monitors the sound environment so that if there is noise louder than the TV’s audio, it will increase the volume of just the dialogue audio so as not to overwhelm users while ensuring no word goes unheard. Also, sound will be delivered seamlessly thanks to real-time deep learning audio separation technology, high-performance NPU (Neural Processing Unit).

AI Streaming for Minimal Data Loss

Thanks to the widespread use of the Over the Top (OTT) streaming services, more and more users are taking advantage of their large screen TVs and stream 8K content. However, existing network infrastructures cannot always guarantee image quality that meets users’ high-resolution expectations. This is why at the Samsung Developers’ Conference in 2019, Samsung introduced its AI Scalenet technology, designed to overcome these infrastructure limitations and support effective 8K streaming and low-latency livestreaming.

AI Scalenet is a CES 2020 Innovation Award-winning AI codec technology that generates resolutions four times higher than conventional technologies without any change to the network infrastructure. It minimizes the data loss that may occur during the compression and playing of videos through deep learning technologies, meaning users can enjoy 8K-quality content regardless of their network infrastructure. Even during peak usage, AI Scalenet dramatically improves image quality and content speed according to the network status and reduces picture breaking and ambient noise.

These days, more content than ever can be enjoyed on our TVs, meaning that the expectation for immersive viewing experiences in the home has increased, too. Samsung plans to continue to use a range of innovative technologies, starting with artificial intelligence, to bring the best experience 8K content and audio experiences to living rooms across the world.

Samsung Electronics, a world leader in advanced semiconductor technology, today announced at its Samsung Tech Day 2019 two silicon products specifically tailored for future mobile devices that will make intensive use of video and artificial intelligence (AI) applications as well as 5G communications.

Both the Exynos 990 premium mobile processor and ultra-fast next-generation 5G Exynos Modem 5123 harness the most advanced 7-nanometer (nm) process technology using extreme ultra-violet (EUV) to provide unprecedented performance and accelerated product development options for mobile manufacturers.

“Milestones in technological advancements are imminent all around us. Mobile 5G technology is opening new avenues for communication and connection, while AI is poised to become an everyday tool for people worldwide,” noted Inyup Kang, president of System LSI Business at Samsung Electronics. “Samsung’s Exynos 990 and Exynos Modem 5123 are perfectly adapted for high-volume 5G and AI applications, and are designed to help the world’s most ambitious enterprises, large and small, achieve their goals of bringing new capabilities to their markets .”

New levels of mobile gaming and other graphics-intensive operations are enabled by the Exynos 990’s inclusion of an embedded Arm Mali-G77 GPU, the first premium GPU based on the new Valhall architecture, which improves graphic performance or power efficiency by up to 20 percent. This comes in addition to an overall 20-percent performance boost from an extremely powerful and flexible tri-cluster CPU structure that consists of two powerful custom cores, two high-performance Cortex-A76 cores and four power-efficient Cortex-A55 cores.

The Exynos 990 also makes on-device AI practical and useful, with a top-class dual-core neural processing unit (NPU) and improved digital signal processor (DSP) that can perform over ten-trillion operations (TOPs) per second.

The NPU enables localized AI in a smartphone or other mobile platform, allowing data to be processed on-device, rather than going through a network and a server, for added efficiency and security. This can also help enhance AI features such as facial recognition and scene detection for richer mobile experiences.

Next-generation mobile connectivity needs are addressed by the 5G Exynos Modem 5123, one of the first 5G modem chips manufactured using a 7nm EUV process. It supports virtually all networks, from 5G’s sub-6GHz and mmWave spectrums to 2G GSM/CDMA, 3G WCDMA, TD-SCDMA, HSPA and 4G LTE, with outstanding downlink speed across the board.  In 5G, with up to 8-carrier aggregation (8CA), the modem delivers a maximum downlink speed of up to 5.1-gigabits per second (Gbps) in sub-6-gigahertz (GHz) and 7.35Gbps in mmWave, or up to 3.0Gbps in 4G networks by supporting higher-order 1024 Quadrature Amplitude Modulation (QAM).

The Exynos 990 complements these modem speeds with a very wide memory bandwidth that supports LPDDR5 data rates of up to 5,500 megabits per second (Mb/s). The processor also features a 120Hz refresh-rate display driver, which makes games come alive by reducing screen tearing and enabling smoother animations even on devices with multiple displays, such as foldable phones. Also on board is an advanced image signal processor (ISP) that supports up to six individual image sensors with concurrent processing of three; this enables pro-grade photography, with resolution up to 108-megapixels.

The Exynos 990 and Exynos Modem 5123 are expected to begin mass production by the end of this year.

For more information about Samsung’s Exynos products, please visit http://www.samsung.com/exynos

Samsung Electronics last month announced its goal to strengthen its leadership in the global system semiconductor industry by 2030 through expanding its proprietary NPU technology development. The company recently delivered an update to this goal at the conference on Computer Vision and Pattern Recognition (CVPR), one of the top academic conferences in computer vision fields.

This update is the company’s development of its On-Device AI lightweight algorithm, introduced at CVPR with a paper titled “Learning to Quantize Deep Networks by Optimizing Quantization Intervals With Task Loss”. On-Device AI technologies directly compute and process data from within the device itself. Over 4 times lighter and 8 times faster than existing algorithms, Samsung’s latest algorithm solution is dramatically improved from previous solutions and has been evaluated to be key to solving potential issues for low-power, high-speed computations.

Streamlining the Deep Learning Process

Samsung Advanced Institute of Technology (SAIT) has announced that they have successfully developed On-Device AI lightweight technology that performs computations 8 times faster than the existing 32-bit deep learning data for servers. By adjusting the data into groups of under 4 bits while maintaining accurate data recognition, this method of deep learning algorithm processing is simultaneously much faster and much more energy efficient than existing solutions.

Samsung’s new On-Device AI processing technology determines the intervals of the significant data that influence overall deep learning performance through ‘learning’. This ‘Quantization¹ Interval Learning (QIL)’ retains data accuracy by re-organizing the data to be presented in bits smaller than their existing size. SAIT ran experiments that successfully demonstrated how the quantization of an in-server deep learning algorithm in 32 bit intervals provided higher accuracy than other existing solutions when computed into levels of less than 4 bits.

When the data of a deep learning computation is presented in bit groups lower than 4 bits, computations of ‘and’ and ‘or’ are allowed, on top of the simpler arithmetic calculations of addition and multiplication. This means that the computation results using the QIL process can achieve the same results as existing processes can while using 1/40 to 1/120 fewer transistors².

As this system therefore requires less hardware and less electricity, it can be mounted directly in-device at the place where the data for an image or fingerprint sensor is being obtained, ahead of transmitting the processed data on to the necessary end points.

The Future of AI Processing and Deep Learning

This technology will help develop Samsung’s system semiconductor capacity as well as strengthening one of the core technologies of the AI era – On-Device AI processing. Differing from AI services that use cloud servers, On-Device AI technologies directly compute data all from within the device itself.

On-Device AI technology can reduce the cost of cloud construction for AI operations since it operates on its own and provides quick and stable performance for use cases such as virtual reality and autonomous driving. Furthermore, On-Device AI technology can save personal biometric information used for device authentication, such as fingerprint, iris and face scans, onto mobile devices safely.

“Ultimately, in the future we will live in a world where all devices and sensor-based technologies are powered by AI,” noted Chang-Kyu Choi, Vice President and head of Computer Vision Lab of SAIT. “Samsung’s On-Device AI technologies are lower-power, higher-speed solutions for deep learning that will pave the way to this future. They are set to expand the memory, processor and sensor market, as well as other next-generation system semiconductor markets.”

A core feature of On-Device AI technology is its ability to compute large amounts of data at a high speed without consuming excessive amounts of electricity. Samsung’s first solution to this end was the Exynos 9 (9820), introduced last year, which featured a proprietary Samsung NPU inside the mobile System on Chip (SoC). This product allows mobile devices to perform AI computations independent of any external cloud server.

Many companies are turning their attention to On-Device AI technology. Samsung Electronics plans to enhance and extend its AI technology leadership by applying this algorithm not only to mobile SoC, but also to memory and sensor solutions in the near future.

Four individuals who played key roles in developing Samsung’s On-Device AI Lightweight Algorithm. From Left to right; Jae-Joon Han, Chang-Young Son, Sang-Il Jung, Chang-Kyu Choi of Samsung Advanced Institute of Technology

1 Quantization is the process of decreasing the number of bits in data by binning the given data into sections of limited number levels, which can be represented in certain bit values and are regarded as having the same value per section

² Transistors are devices that control the flow of current or voltage in a semiconductor by acting as amplifiers or switches