How robust are deep neural networks?
B Sengupta, KJ Friston - arXiv preprint arXiv:1804.11313, 2018 - arxiv.org
Convolutional and Recurrent, deep neural networks have been successful in machine
learning systems for computer vision, reinforcement learning, and other allied fields …
learning systems for computer vision, reinforcement learning, and other allied fields …
[HTML][HTML] Intelligent tennis robot based on a deep neural network
S Gu, W Zeng, Y Jia, Z Yan - Applied Sciences, 2019 - mdpi.com
In this paper, an improved you only look once (YOLOv3) algorithm is proposed to make the
detection effect better and improve the performance of a tennis ball detection robot. The …
detection effect better and improve the performance of a tennis ball detection robot. The …
Banjarese chatbot using seq2seq model
BA Setiawan, E Utami… - 2021 4th International …, 2021 - ieeexplore.ieee.org
The significant development of chatbot technology began with the implementation of the
Seq2Seq (Sequence-to-Sequence) model which is based on two RNN (Recurrent Neural …
Seq2Seq (Sequence-to-Sequence) model which is based on two RNN (Recurrent Neural …
Deep learning to implement a statistical weather forecast for the andean city of quito
RL Cañar, A Fontaine, PL Morillo… - 2020 IEEE …, 2020 - ieeexplore.ieee.org
A weather forecast is classically based on the use of a Physical Model computing
information from Conventional Weather Stations (CWS), Automatic Weather Stations (AWS) …
information from Conventional Weather Stations (CWS), Automatic Weather Stations (AWS) …
Geoseq2seq: Information geometric sequence-to-sequence networks
A Bay, B Sengupta - arXiv preprint arXiv:1710.09363, 2017 - arxiv.org
The Fisher information metric is an important foundation of information geometry, wherein it
allows us to approximate the local geometry of a probability distribution. Recurrent neural …
allows us to approximate the local geometry of a probability distribution. Recurrent neural …
Optimasi Model Percakapan Bahasa Indonesia Berbasis Sequence To Sequence (Seq2seq)
YDWG Made - 2019 - e-journal.uajy.ac.id
Chatbot saat ini berkembang dengan kerangka kerja sequence-to-sequence (SEQ2SEQ)
yang berbasiskan dua Recurrent Neural Network (2-RNN). Seiring waktu, tingkat kesulitan …
yang berbasiskan dua Recurrent Neural Network (2-RNN). Seiring waktu, tingkat kesulitan …