在互補式金氧半(CMOS)積體電路中，隨著量產製程的演進，元件的尺寸已縮減到深次微 米(Deep-submicron)階段，以增進積體電路(IC)的性能及運算速度，以及降低每顆晶片的製造 成本。但隨著元件尺寸的縮減，卻出現一些可靠度的問題。 在次微米技術中，為了克服所謂熱載子(Hot-Carrier)問題而發展出 LDD(Lightly-Doped Drain) 製程與結構; 為了降低 CMOS 元件汲極(drain)與源極(source)的寄生電阻(sheet resistance) Rs 與 Rd，而發展出 Silicide 製程; 為了降低 CMOS 元件閘級的寄生電阻 Rg，而發展出 Polycide 製 程 ; 在更進步的製程中把 Silicide 與 Polycide 一起製造，而發展出所謂 Salicide 製程
標簽： Protection CMOS ESD ICs in
上傳時間： 2020-06-05
上傳用戶：shancjb
在互補式金氧半(CMOS)積體電路中，隨著量產製程 的演進，元件的尺寸已縮減到深次微米(Deep-submicron)階 段，以增進積體電路(IC)的性能及運算速度，以及降低每 顆晶片的製造成本。但隨著元件尺寸的縮減，卻出現一些 可靠度的問題。
標簽： ESD_Technology
上傳時間： 2020-06-05
上傳用戶：shancjb
ESD is a crucial factor for integrated circuits and influences their quality and reliability. Today increasingly sensitive processes with Deep sub micron structures are developed. The integration of more and more functionality on a single chip and saving of chip area is required. Integrated circuits become more susceptible to ESD/EOS related damages. However, the requirements on ESD robustness especially for automotive applications are increasing. ESD failures are very often the reason for redesigns. Much research has been conducted by semiconductor manufacturers on ESD robust design.
標簽： Guidelines Design Basic ESD
上傳時間： 2020-06-05
上傳用戶：shancjb
Signals convey information. Systems transform signals. This book introduces the mathe- matical models used to design and understand both. It is intended for students interested in developing a Deep understanding of how to digitally create and manipulate signals to measure and control the physical world and to enhance human experience and communi- cation.
標簽： Interpretation Structure and Signals Systems of
上傳時間： 2020-06-10
上傳用戶：shancjb
The past decade has seen an explosion of machine learning research and appli- cations; especially, Deep learning methods have enabled key advances in many applicationdomains,suchas computervision,speechprocessing,andgameplaying. However, the performance of many machine learning methods is very sensitive to a plethora of design decisions, which constitutes a considerable barrier for new users. This is particularly true in the booming field of Deep learning, where human engineers need to select the right neural architectures, training procedures, regularization methods, and hyperparameters of all of these components in order to make their networks do what they are supposed to do with sufficient performance. This process has to be repeated for every application. Even experts are often left with tedious episodes of trial and error until they identify a good set of choices for a particular dataset.
標簽： Auto-Machine-Learning-Methods-Sys tems-Challenges
上傳時間： 2020-06-10
上傳用戶：shancjb
Inventors have long dreamed of creating machines that think. This desire dates back to at least the time of ancient Greece. The mythical figures Pygmalion, Daedalus, and Hephaestus may all be interpreted as legendary inventors, and Galatea, Talos, and Pandora may all be regarded as artificial life ( , Ovid and Martin 2004 Sparkes 1996 Tandy 1997 ; , ; , ).
上傳時間： 2020-06-10
上傳用戶：shancjb
We’re living through exciting times. The landscape of what computers can do is changing by the week. Tasks that only a few years ago were thought to require higher cognition are getting solved by machines at near-superhuman levels of per- formance. Tasks such as describing a photographic image with a sentence in idiom- atic English, playing complex strategy game, and diagnosing a tumor from a radiological scan are all approachable now by a computer. Even more impressively, computers acquire the ability to solve such tasks through examples, rather than human-encoded of handcrafted rules.
標簽： Deep-Learning-with-PyTorch
上傳時間： 2020-06-10
上傳用戶：shancjb
Although state of the art in many typical machine learning tasks, Deep learning algorithmsareverycostly interms ofenergyconsumption,duetotheirlargeamount of required computations and huge model sizes. Because of this, Deep learning applications on battery-constrained wearables have only been possible through wireless connections with a resourceful cloud. This setup has several drawbacks. First, there are privacy concerns. Cloud computing requires users to share their raw data—images, video, locations, speech—with a remote system. Most users are not willing to do this. Second, the cloud-setup requires users to be connected all the time, which is unfeasible given current cellular coverage. Furthermore, real-time applications require low latency connections, which cannot be guaranteed using the current communication infrastructure. Finally, wireless connections are very inefficient—requiringtoo much energyper transferredbit for real-time data transfer on energy-constrained platforms.
標簽： Embedded_Deep_Learning Algorithms
上傳時間： 2020-06-10
上傳用戶：shancjb
上面是一段實時目標識別的演示， 計算機在視頻流上標注出物體的類別， 包括人、汽車、自行車、狗、背包、領帶、椅子等。今天的計算機視覺技術已經可以在圖片、視頻中識別出大量類別的物體， 甚至可以初步理解圖片或者視頻中的內容， 在這方面，人工智能已經達到了3 歲兒童的智力水平。這是一個很了不起的成就， 畢竟人工智能用了幾十年的時間， 就走完了人類幾十萬年的進化之路，并且還在加速發展。道路總是曲折的， 也是有跡可循的。在嘗試了其它方法之后， 計算機視覺在仿生學里找到了正確的道路（至少目前看是正確的） 。通過研究人類的視覺原理，計算機利用深度神經網絡（ Deep Neural Network，NN）實現了對圖片的識別，包括文字識別、物體分類、圖像理解等。在這個過程中，神經元和神經網絡模型、大數據技術的發展，以及處理器（尤其是GPU）強大的算力，給人工智能技術的發展提供了很大的支持。本文是一篇學習筆記， 以深度優先的思路， 記錄了對深度學習（Deep Learning）的簡單梳理，主要針對計算機視覺應用領域。
上傳時間： 2022-06-22
上傳用戶：
Introduction The Sil9135/Sil9135A HDMI Receiver with Enhanced Audio and Deep Color Outputs is a second-generation dual-input High Definition Multimedia Interface(HDMI)receiver. It is software-compatible with the Sil9133receiver, but adds audio support for DTS-HD and Dolby TrueHD. Digital televisions that can display 10-or 12-bit color depth can now provide the highest quality protected digital audio and video over a single cable. The Sil9135and Sil9135A devices, which are functionally identical, can receive Deep Color video up to 12-bit,1080p @60Hz. Backward compatibility with the DVI 1.0specification allows HDMI systems to connect to existing DVI 1.0 hosts, such as HD set-top boxes and PCs. Silicon Image HDMI receivers use the latest generation Transition Minimized Differential Signaling(TMDS) core technology that runs at 25-225 MHz.The chip comes pre-programmed with High-bandwidth?
上傳時間： 2022-06-25
上傳用戶：
