Results 21 to 30 of about 12,936,285 (295)

Consistent Sparse Deep Learning: Theory and Computation [PDF]

Journal of the American Statistical Association, 2021
Deep learning has been the engine powering many successes of data science. However, the deep neural network (DNN), as the basic model of deep learning, is often excessively over-parameterized, causing many difficulties in training, prediction and interpretation.
Yan Sun 0011, Qifan Song, Faming Liang
openaire   +4 more sources

The Computational Magic of the Ventral Stream: Towards a Theory [PDF]

, 2011
I conjecture that the sample complexity of object recognition is mostly due to geometric image transformations and that a main goal of the ventral stream – V1, V2, V4 and IT – is to learn-and-discount image transformations.
Tomaso A. Poggio, Tomaso Poggio
core   +1 more source

Schema Theory-based Computational Approach to Support Children's Conceptual Understanding [PDF]

, 2006
Researchers acknowledge the difficulty faced by children in understanding new concepts. Explaining new concepts to children requires supporting their reasoning based on concrete objects and ideas.
Ibrahim, Zukeri
core   +4 more sources

Energy-Efficient Trajectory Planning With Joint Device Selection and Power Splitting for mmWaves-Enabled UAV-NOMA Networks

IEEE Transactions on Machine Learning in Communications and Networking
This paper proposes two energy-efficient reinforcement learning (RL)-based algorithms for millimeter wave (mmWave)-enabled unmanned aerial vehicle (UAV) communications toward beyond-5G (B5G).
Ahmad Gendia, Osamu Muta, Sherief Hashima, Kohei Hatano   +3 more
doaj   +1 more source

Game Theory Meets Computational Learning Theory (Dagstuhl Seminar 17251)

, 2017
his report documents the program and the outcomes of Dagstuhl Seminar 17251 "Game Theory Meets Computational Learning Theory". While there have been many Dagstuhl seminars on various aspects of Algorithmic Game Theory, this was the first one to focus ...
Dütting, Paul, Goldberg, Paul W., Mansour, Yishay   +2 more
core   +1 more source

On Similarities between Inference in Game Theory and Machine Learning [PDF]

, 2008
In this paper, we elucidate the equivalence between inference in game theory and machine learning. Our aim in so doing is to establish an equivalent vocabulary between the two domains so as to facilitate developments at the intersection of both fields ...
Stephen J. Roberts, Leslie, D., Roberts, S. J., Jennings, Nick, Jennings, N. R., Rogers, A, Leslie, D, Dash, Rajdeep K., Dash, R, Steven Reece, Leslie, David S., Rajdeep K. Dash, Dash, Rajdeep, Rezek, Iead, Rogers, Alex, Reece, S., Rezek, I., Jennings, N, Iead Rezek, Rezek, I, Rogers, A., Dash, R. K., Roberts, S, Nicholas R. Jennings, Jennings, Nicholas R., Roberts, Stephen J., Reece, S, Reece, Steven, David S. Leslie   +28 more
core   +2 more sources

EVIDENCE FOR THE INFLUENCE OF CONFUCIAN SOCIAL LEARNING THEORY ON NEGATIVE BEHAVIORAL OUTCOMES [PDF]

, 2021
This study is a test of Confucian social learning theory’s ability to influence negative behavioral outcomes among young people. Material relating to learning from different social environments and the attendant behavioral outcomes was filtered out of an
Lassi, Nicholas
core   +1 more source

Guest Editorial: Special Section on Computational Intelligence in Antennas and Propagation: Emerging Trends and Applications

IEEE Open Journal of Antennas and Propagation, 2021
Computational Intelligence (CI) is the theory, design, application and development of biologically and linguistically motivated computational paradigms.
Sotirios K. Goudos, Dimitris E. Anagnostou, Zikri Bayraktar, Sawyer D. Campbell, Paolo Rocca, Douglas H. Werner   +5 more
doaj   +1 more source

RIS-Assisted SWIPT for IoT Networks: A Survey of Architectures, Optimization, and Future Directions

IEEE Open Journal of the Communications Society
The fusion of Simultaneous Wireless Information and Power Transfer (SWIPT) with Reconfigurable Intelligent Surfaces (RISs), i.e., RIS-aided SWIPT, is emerging as a promising paradigm for sustainable, energy-efficient, and intelligent sixth-generation (6G)
Sherief Hashima, Mostafa Fouda, Kohei Hatano, Eiji Takimoto, Osamu Muta, Ahmad Gendia   +5 more
doaj   +1 more source

Bias-variance decomposition in Genetic Programming

Open Mathematics, 2016
We study properties of Linear Genetic Programming (LGP) through several regression and classification benchmarks. In each problem, we decompose the results into bias and variance components, and explore the effect of varying certain key parameters on the
Kowaliw Taras, Doursat René
doaj   +1 more source