Neural architecture searchNeural architecture search (NAS) is a technique for automating the design of artificial neural networks (ANN), a widely used model in the field of machine learning. NAS has been used to design networks that are on par or outperform hand-designed architectures. Methods for NAS can be categorized according to the search space, search strategy and performance estimation strategy used: The search space defines the type(s) of ANN that can be designed and optimized. The search strategy defines the approach used to explore the search space.
Deep reinforcement learningDeep reinforcement learning (deep RL) is a subfield of machine learning that combines reinforcement learning (RL) and deep learning. RL considers the problem of a computational agent learning to make decisions by trial and error. Deep RL incorporates deep learning into the solution, allowing agents to make decisions from unstructured input data without manual engineering of the state space. Deep RL algorithms are able to take in very large inputs (e.g.
Red SeaThe Red Sea (البحر الأحمر - بحر القلزم ; יַם-סוּף or הַיָּם הָאָדְוֹם ; Coptic: ⲫⲓⲟⲙ ⲛ̀ϩⲁϩ Phiom Enhah or ⲫⲓⲟⲙ ⲛ̀ϣⲁⲣⲓ Phiom ǹšari; Tigrinya: ቀይሕ ባሕሪ Qeyih Bahri; Badda Cas 𐒁𐒖𐒆𐒆𐒖 𐒋𐒖𐒈) is a seawater inlet of the Indian Ocean, lying between Africa and Asia. Its connection to the ocean is in the south, through the Bab el Mandeb strait and the Gulf of Aden. To its north lie the Sinai Peninsula, the Gulf of Aqaba, and the Gulf of Suez (leading to the Suez Canal). It is underlain by the Red Sea Rift, which is part of the Great Rift Valley.
Deep image priorDeep image prior is a type of convolutional neural network used to enhance a given image with no prior training data other than the image itself. A neural network is randomly initialized and used as prior to solve inverse problems such as noise reduction, super-resolution, and inpainting. Image statistics are captured by the structure of a convolutional image generator rather than by any previously learned capabilities.
Underwater environmentAn underwater environment is a environment of, and immersed in, liquid water in a natural or artificial feature (called a body of water), such as an ocean, sea, lake, pond, reservoir, river, canal, or aquifer. Some characteristics of the underwater environment are universal, but many depend on the local situation. Liquid water has been present on Earth for most of the history of the planet. The underwater environment is thought to be the place of the origin of life on Earth, and it remains the ecological region most critical to the support of life and the natural habitat of the majority of living organisms.
VideoVideo is an electronic medium for the recording, copying, playback, broadcasting, and display of moving media. Video was first developed for mechanical television systems, which were quickly replaced by cathode-ray tube (CRT) systems which, in turn, were replaced by flat panel displays of several types. Video systems vary in display resolution, aspect ratio, refresh rate, color capabilities and other qualities. Analog and digital variants exist and can be carried on a variety of media, including radio broadcasts, magnetic tape, optical discs, , and network streaming.
Object detectionObject detection is a computer technology related to computer vision and that deals with detecting instances of semantic objects of a certain class (such as humans, buildings, or cars) in digital images and videos. Well-researched domains of object detection include face detection and pedestrian detection. Object detection has applications in many areas of computer vision, including and video surveillance. It is widely used in computer vision tasks such as , vehicle counting, activity recognition, face detection, face recognition, video object co-segmentation.
Climate changeIn common usage, climate change describes global warming—the ongoing increase in global average temperature—and its effects on Earth's climate system. Climate change in a broader sense also includes previous long-term changes to Earth's climate. The current rise in global average temperature is more rapid than previous changes, and is primarily caused by humans burning fossil fuels. Fossil fuel use, deforestation, and some agricultural and industrial practices increase greenhouse gases, notably carbon dioxide and methane.
Computer visionComputer vision tasks include methods for , , and understanding digital images, and extraction of high-dimensional data from the real world in order to produce numerical or symbolic information, e.g. in the forms of decisions. Understanding in this context means the transformation of visual images (the input to the retina in the human analog) into descriptions of the world that make sense to thought processes and can elicit appropriate action.
Online machine learningIn computer science, online machine learning is a method of machine learning in which data becomes available in a sequential order and is used to update the best predictor for future data at each step, as opposed to batch learning techniques which generate the best predictor by learning on the entire training data set at once. Online learning is a common technique used in areas of machine learning where it is computationally infeasible to train over the entire dataset, requiring the need of out-of-core algorithms.
Automated machine learningAutomated machine learning (AutoML) is the process of automating the tasks of applying machine learning to real-world problems. AutoML potentially includes every stage from beginning with a raw dataset to building a machine learning model ready for deployment. AutoML was proposed as an artificial intelligence-based solution to the growing challenge of applying machine learning. The high degree of automation in AutoML aims to allow non-experts to make use of machine learning models and techniques without requiring them to become experts in machine learning.
Visual temporal attentionVisual temporal attention is a special case of visual attention that involves directing attention to specific instant of time. Similar to its spatial counterpart visual spatial attention, these attention modules have been widely implemented in video analytics in computer vision to provide enhanced performance and human interpretable explanation of deep learning models.
