Filters








445,074 Hits in 9.0 sec

To go deep or wide in learning? [article]

Gaurav Pandey, Ambedkar Dukkipati
2014 arXiv   pre-print
To achieve acceptable performance for AI tasks, one can either use sophisticated feature extraction methods as the first layer in a two-layered supervised learning model, or learn the features directly  ...  We propose exact and inexact learning strategies for wide learning and show that wide learning with single layer outperforms single layer as well as deep architectures of finite width for some benchmark  ...  Inexact Deep-Wide Learning Exact learning of the kernel matrix as given above requires the entire matrix to be present in memory.  ... 
arXiv:1402.5634v1 fatcat:o6dzmdqmijahrlwlfpyjqcata4

Learning machine learning

Ted G. Lewis, Peter J. Denning
2018 Communications of the ACM  
, image segmentation and even to master the game Go.  ...  physics is teaming up with experiments at CERN and beyond to train young researchers in the arts of deep learning.  ... 
doi:10.1145/3286868 fatcat:fuxvgt2bonfrtp5yggmyhmyhlm

Learning about Learning

Rishi Sriram
2018 About Campus Enriching the Student Learning Experience  
We need to jump sideways or over a wall (or go in a new direction and see around the wall) to be a university we hadn't been before. We also need to work with faculty.  ...  Pretty soon, some argue, we won't need mortar or buildings at all-we will simply go to college in the cloud.  ... 
doi:10.1177/1086482218765747 fatcat:wopauankmjfyld4ftxehzxc2aq

Reinforcement Evolutionary Learning Method for self-learning [article]

Kumarjit Pathak, Jitin Kapila
2018 arXiv   pre-print
Quantitative research is the most widely spread application of data science in Marketing or financial domain where applicability of state of the art reinforcement learning for auto-learning is less explored  ...  There are state of the art methodologies to detect the impact of concept drift, however general strategy considered to overcome the issue in performance is to rebuild or re-calibrate the model periodically  ...  Challenge of self-learning, auto-learning and concept drift is wide across industries.  ... 
arXiv:1810.03198v1 fatcat:xdrufyoocbe5ji34pdbdvcn52y

Deepening Learning through Learning-by-Inventing

Mikko Apiola, Matti Tedre
2013 Journal of Information Technology Education Innovations in Practice  
approaches to problem solving and management, and the use of robotics to facilitate deep learning strategies.  ...  Executive Summary It has been shown that deep approaches to learning, intrinsic motivation, and self-regulated learning have strong positive effects on learning.  ...  and then we decided what we are going to do.  ... 
doi:10.28945/1885 fatcat:6nnbperb4zdcldbgt6xy2roadu

Deep Learning

Nikita Patil, Krishna Kadam, Rahul Patil
2018 IJARCCE  
Deep learning is used to identify the objects with the help of neural network. It is used to identify various objects in the world.  ...  In this, we have explained the process of identifying the objects with the help of various layers.  ...  CONCLUSION In this we have studied and gathered the information about deep learning and how it is going to change the world in the future.  ... 
doi:10.17148/ijarcce.2018.7820 fatcat:yrnkneeorjbxdapyhbtmjx7qjy

Learning to reinforcement learn [article]

Jane X Wang, Zeb Kurth-Nelson, Dhruva Tirumala, Hubert Soyer, Joel Z Leibo, Remi Munos, Charles Blundell, Dharshan Kumaran, Matt Botvinick
2017 arXiv   pre-print
In the present work we introduce a novel approach to this challenge, which we refer to as deep meta-reinforcement learning.  ...  In recent years deep reinforcement learning (RL) systems have attained superhuman performance in a number of challenging task domains.  ...  Go .  ... 
arXiv:1611.05763v3 fatcat:onugpzs7obg2phnzdwk6rith7y

Network Representation Learning: From Traditional Feature Learning to Deep Learning

Ke Sun, Lei Wang, Bo Xu, Wenhong Zhao, Shyh Wei Teng, Feng Xia
2020 IEEE Access  
In this survey, we try to go through the development of data representation in graphstructured data from TFL to recent NRL based on deep learning.  ...  DEEP LEARNING-BASED MODELS We have witnessed the superior performance of deep learning in many fields, and they have been widely applied for image classification, speech recognition, and object detection  ... 
doi:10.1109/access.2020.3037118 fatcat:kca6htfarjdjpmtwcvbsppfzui

The Implementation of Deep Reinforcement Learning in E-Learning and Distance Learning: Remote Practical Work

Abdelali El Gourari, Mustapha Raoufi, Mohammed Skouri, Fahd Ouatik, Salvatore Carta
2021 Mobile Information Systems  
The objective of this work is to propose a recommendation system based on deep quality-learning networks (DQNs) to recommend and direct students in advance of doing the RPW according to their skills of  ...  each mouse or keyboard click per student.  ...  However, there is a challenge when we contrast deep RL to deep learning: Nonstationary target: let us go back to the algorithm for deep Q-learning where W is the weight of the network [20] .  ... 
doi:10.1155/2021/9959954 fatcat:3x4kk7mrzjbq3o5m6ueor2o72q

Machine learning and deep learning

Christian Janiesch, Patrick Zschech, Kai Heinrich
2021 Electronic Markets  
In this article, we summarize the fundamentals of machine learning and deep learning to generate a broader understanding of the methodical underpinning of current intelligent systems.  ...  These naturally go beyond technological aspects and highlight issues in human-machine interaction and artificial intelligence servitization.  ...  This is the networks' core capability, which is commonly known as deep learning.  ... 
doi:10.1007/s12525-021-00475-2 fatcat:k6mhktpp3jdy7jgwoipznzks6e

Portfolio Learning Based on Deep Learning

Wei Pan, Jide Li, Xiaoqiang Li
2020 Future Internet  
In this paper, we propose a novel portfolio learning approach based on deep learning and apply it to China's stock market.  ...  Specifically, this method is based on the similarity of deep features extracted from candlestick charts.  ...  Deep learning models based on time series have been widely used for stock prediction.  ... 
doi:10.3390/fi12110202 fatcat:wr63if7zqjbppaoyenek3xflxm

Learning with Random Learning Rates [article]

Léonard Blier, Pierre Wolinski, Yann Ollivier
2019 arXiv   pre-print
Hyperparameter tuning is a bothersome step in the training of deep learning models. One of the most sensitive hyperparameters is the learning rate of the gradient descent.  ...  We present the 'All Learning Rates At Once' (Alrao) optimization method for neural networks: each unit or feature in the network gets its own learning rate sampled from a random distribution spanning several  ...  Acknowledgments We would like to thank Corentin Tallec for his technical help, and his many remarks and advice.  ... 
arXiv:1810.01322v3 fatcat:hqtaywiw4rgepmul7xr5zj7t4a

Patterns in Student Learning: Relationships Between Learning Strategies, Conceptions of Learning, and Learning Orientations

Jan D. Vermunt, Yvonne J. Vermetten
2004 Educational Psychology Review  
, namely, cognitive processing strategies, metacognitive regulation strategies, conceptions of learning, and learning orientations; and/or (b) an integrative learning theory focussing on the interplay  ...  This paper reviews the research conducted in the last decade on patterns in student learning, mostly in higher education.  ...  how to go about learning are no longer adequate (Vermunt and Verloop, 1999) .  ... 
doi:10.1007/s10648-004-0005-y fatcat:l5djgzviafcdpjrkvimcrb62ve

Artificial Intelligence, Machine Learning and Deep Learning In Healthcare

Uzma Anjum
2021 Bioscience Biotechnology Research Communications  
AI is a concept based on the imitation of human intelligence in computers trained to think and act in a human-like way.  ...  The pinnacle achievement in this field will be to build a computer that can imitate or outperform human mental abilities such as thinking, comprehension, imagination, vision, recognition, creativity, and  ...  METHODOLOGY Artificial intelligence (AI) has advanced in recent years for a wide range of machine learning approaches, including deep learning, reinforcement learning, and transfer learning.  ... 
doi:10.21786/bbrc/14.7.36 fatcat:5i7lgz3ybfconmnyddpemtbfua

Deep learning in imaging

Rita Strack
2018 Nature Methods  
Machine learning approaches that include deep learning are moving beyond image classification to change the way images are made.  ...  Researchers have also used deep learning to go from low signalto-noise images to high-quality images, which opens the door to extended imaging of even very light-sensitive living organisms (Nat.  ...  Conventional machine learning approaches are widely used for segmentation and phenotyping in fluorescence microscopy.  ... 
doi:10.1038/s41592-018-0267-9 fatcat:bov6gnfnyrdrlai7v5meli35tq
« Previous Showing results 1 — 15 out of 445,074 results