Deep Learning Systems
Algorithms, Compilers, and Processors for Large-Scale Production
Chapter and Conference Paper
The fields of HCI and interactive art have long maintained an increasingly fruitful relationship of dialogue, exchange, cross-pollination, and complementation. From an art perspective, HCI knowledge and strate...
Article
The metaphor of technical debt (TD) has generated a conceptual framework on factors that weaken the quality of software and accumulate a repair cost. However, user-related aspects like user experience (UX) rec...
Article
WRF wind forecasts from four operative schemes used by OHMC (Observatorio HidroMeteorológico de Córdoba), a test scheme (WRF-E) and two daily runs with 4 km horizontal resolution were analyzed. Wind simulation...
Chapter and Conference Paper
This study aims to assess the performance of a solar/gas assisted absorption chiller using NH3/LiNO3 for air conditioning in malls at the environmental conditions of the city of Barranquilla, Colombia. The perfor...
Chapter and Conference Paper
In-vehicle information systems (IVIS) represent a growing industry. IVIS were originally built and deployed by car manufacturers, which ensured that they complied with the safety regulations of the car industr...
Chapter and Conference Paper
We study how STEM students experience the use of smart glasses for the first time. We evaluate the glasses’ usability, degree of technological acceptance, experience, and elicited emotional response. To this e...
Chapter and Conference Paper
Awareness is of paramount importance to effective collaboration. Groupware systems have traditionally implemented awareness in the form of visual cues. With the advent of alternatives user interface strategies...
Chapter and Conference Paper
The steady evolution of wearable technology—along with augmented reality (AR)—has enabled important advances in teaching and learning. We present STEM Education, an interactive AR application for smart glasses. W...
Chapter
There are four main types of NN topologies used in commercial applications: multilayer perceptrons (MLPs), convolution neural networks (CNNs), recurrent neural networks (RNNs), and transformer-based topologies...
Chapter
At the core of the software stack are compilers to transform the programmer’s high-level code into executable code that runs efficiently on a target device. Programmers use a variety of languages to code at va...
Chapter
In this concluding chapter, we discuss some of the opportunities and challenges ahead. The opportunities include using ML techniques to improve various aspects of the overall DL system. The challenges include ...
Chapter
The number of computations required to train state-of-the-art models is growing exponentially, doubling every ~ 3:4 months (far below the glory days of Moore’s Law 1.5–2 years) [DH18]. Training a large model c...
Chapter and Conference Paper
User experience (UX) is related to the feelings and emotions that people undergo when interacting with technology. This concept also applies to wearable devices, such as smart glasses, which have been widely a...
Chapter
Training a model to achieve high statistical performance within a computational and power budget requires several design considerations. These include defining a topology, preparing the dataset, properly initi...
Chapter
Computers represent real numerical values as a set of binary digits or bits, usually with 8, 16, 32, or 64 bits. The more bits used, the higher the numerical range and precision or representation of the numeri...
Book
Chapter
A deep learning (DL) model is a function that maps input data to an output prediction. To improve the accuracy of the prediction in complex tasks, DL models are increasingly requiring more compute, memory, ban...
Chapter
The main types of workloads where DL models are used in production are recommender systems, computer vision, and NLP.
Chapter
The primary components in a DL platform are multitudinous multiplication and addition units, sufficient memory capacity, high memory bandwidth to feed the compute units, high inter-node and inter-server bandwi...
Chapter
A framework has multiple types of compilers: the computation graph optimizer, the primitive libraries JIT to select the best schedule, the code generation path for operations not supported by the primitive lib...