Book Chapter10.1016/b978-0-323-85280-7.00013-0
Deep learning with connectomes
01 Jan 2023
- pp 289-308
2
TL;DR: Deep learning is a class of machine learning methods that have recently produced state-of-the-art results in a number of classic computer vision and image analysis problems as mentioned in this paper , which use highly nonlinear neural network models to learn useful representations of the data for the prediction task at hand.
read more
Abstract: Deep learning is a class of machine learning methods that have recently produced state-of-the-art results in a number of classic computer vision and image analysis problems. These methods use highly nonlinear neural network models to learn useful representations of the data for the prediction task at hand. This chapter covers the application of deep learning models to connectome data analysis, reviewing popular types of neural network architectures, practical steps for training and evaluating a deep learning model, and limitations and potential future work in developing deep learning models for connectomes.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Strategies for overcoming data scarcity, imbalance, and feature selection challenges in machine learning models for predictive maintenance
Ali Hakami
TL;DR: This study proposes an ML-based approach that adapts to these hurdles through the generation of synthetic data, temporal feature extraction, and the creation of failure horizons in Predictive maintenance.
16
Volatile and Nonvolatile Programmable Iontronic Memristor with Lithium Imbued TiO<sub><i>x</i></sub> for Neuromorphic Computing Applications
TL;DR: Researchers develop a lithium-imbued TiOx iontronic device with volatile and nonvolatile memory capabilities, exhibiting synapse-like behavior and high uniformity, enabling neuromorphic computing applications with 94.4% accuracy in voice recognition tasks.
2
References
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
99K
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
67K
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
- 01 Jan 1998
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
53.5K
•Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.