Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

An introduction to a broad range of topics in deep learning, covering mathematical and conceptual background, deep learning techniques used in industry, and research perspectives. Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Probability theory --- Information systems --- Artificial intelligence. Robotics. Simulation. Graphics --- Mathematical linguistics --- analyse (wiskunde) --- Machine learning. --- Artificiële intelligentie --- Machine learning --- Learning, Machine --- Artificial intelligence --- Machine theory --- למידה חשובית --- Apprentissage automatique --- Machine Learning --- Apprentissage automatique. --- Transfer Learning --- Learning, Transfer --- Machinaal leren --- 681.3*I2 --- 681.3*I2 Artificial intelligence. AI --- Artificial intelligence. AI --- deep learning --- machine learning --- artificiële intelligentie (AI) --- Informatique --- Intelligence artificielle

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This book is a collection of the accepted papers presented at the Workshop on Artificial Intelligence with Biased or Scarce Data (AIBSD) in conjunction with the 36th AAAI Conference on Artificial Intelligence 2022. During AIBSD 2022, the attendees addressed the existing issues of data bias and scarcity in Artificial Intelligence and discussed potential solutions in real-world scenarios. A set of papers presented at AIBSD 2022 is selected for further publication and included in this book.

Technology: general issues. --- Artificial intelligence --- History of engineering & technology. --- permutation equivariance --- optimization --- gender bias --- fairness --- face-recognition models --- facial attributes --- social bias --- bias detection --- natural language processing --- temporal bias --- forecasting --- contrastive learning --- supervised contrastive learning --- transfer learning --- robustness --- noisy labels --- coresets --- deep learning --- contextualized embeddings --- out-of-distribution generalization

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Many recent studies on medical image processing have involved the use of machine learning (ML) and deep learning (DL). This special issue, “Machine Learning/Deep Learning in Medical Image Processing”, has been launched to provide an opportunity for researchers in the area of medical image processing to highlight recent developments made in their fields with ML/DL. Seven excellent papers that cover a wide variety of medical/clinical aspects are selected in this special issue.

Technology: general issues --- pancreas --- segmentation --- computed tomography --- deep learning --- data augmentation --- neoplasm metastasis --- ovarian neoplasms --- radiation exposure --- tomography --- x-ray computed --- prostate carcinoma --- microscopic --- convolutional neural network --- machine learning --- handcrafted --- oral carcinoma --- medical image segmentation --- colon cancer --- colon polyps --- OCT --- optical biopsy --- animal rat models --- CADx --- airway volume analysis --- artificial intelligence --- coronary artery disease --- SPECT MPI scans --- convolutional neural networks --- transfer learning --- classification models --- n/a

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Nerve sheath tumors can be a significant cause of morbidity for many patients. These include benign tumors such as schwannomas, diffuse and plexiform neurofibromas, and atypical neurofibromas, as well as the aggressive soft tissue sarcoma known as the malignant peripheral nerve sheath tumor (MPNST). Nerve sheath tumors occur sporadically and in the context of the clinical neuro-genetic tumor predisposition syndromes neurofibromatosis type 1 (NF1) and type 2 (NF2). Historically, the mainstay of treatment for nerve sheath tumors has been surgery. However, for both benign and malignant nerve sheath tumors, there is a high recurrence rate, highlighting the pressing need for novel therapies. As we have entered the genomic era, the hope is that an improved understanding of the genetics, and therefore the biology, of these tumors will ultimately lead to therapies that result in better outcomes. In this Special Issue, we include both review articles and original research related to the genomic understanding and modeling of schwannomas, plexiform and diffuse neurofibromas, atypical neurofibromas, and malignant peripheral nerve sheath tumors as well as genomic methods being developed and applied to advance our understanding of these tumors.

Medicine --- neurofibromatosis type 1 --- nerve sheath tumor --- cancer --- latent variables --- machine learning --- supervised learning --- transfer learning --- random forest --- metaVIPER --- tumor deconvolution --- neurofibromatosis --- malignant peripheral nerve sheath tumor --- MPNST --- polycomb repressive complex --- PRC2 --- NF1 --- kinase --- kinome adaptation --- kinome reprogramming --- MET --- MEK --- doxorubicin --- capmatinib --- tram --- genomics --- tumor evolution --- pathology --- next generation sequencing --- clinical genetics --- malignant peripheral nerve sheath tumors --- plexiform neurofibromas --- Schwann cells --- neurofibromatosis type 1 syndrome --- neurofibromin 1 --- genetically engineered mouse models --- heterogeneity --- CRISPR/Cas9 --- mouse models --- sarcoma --- tumor microenvironment --- neurofibromatosis 1 (NF1) --- mebendazole (MBZ) --- COX-2 inhibitor --- malignancy --- chemoprevention --- nerve sheath tumors

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Data science is an emerging multidisciplinary field which lies at the intersection of computer science, statistics, and mathematics, with different applications and related to data mining, deep learning, and big data. This Special Issue on “Principles and Applications of Data Science” focuses on the latest developments in the theories, techniques, and applications of data science. The topics include data cleansing, data mining, machine learning, deep learning, and the applications of medical and healthcare, as well as social media.

Technology: general issues --- History of engineering & technology --- deep learning --- user preference learning --- feature fusion --- similar user recommendation --- convolutional neural network --- image classification --- electronic health records --- fair exchange --- forward secrecy --- raw material --- mining --- terminology --- dictionary --- terminology application --- mobile application --- digitization --- lexical data --- corpus data --- linguistic linked open data --- neuro-fuzzy --- prediction model --- air pollution --- PM2.5 --- PM10 --- self-attention mechanism --- graph neural network --- data mining --- behaviour sequence pattern --- behaviour network --- water crystal --- fine-tuning --- supervised --- classification --- combined classification model --- deep transfer learning --- focal-segmental --- kidney disease --- kidney glomeruli --- medical image --- sclerosed glomeruli --- predictive analytics --- Internet of Things --- peasant farming --- smart farming system --- crop production prediction