fixes

main.bib

@@ -2255,3 +2255,51 @@ Conclusion(s): Measuring urinary LH levels is an excellent method for determinin
 	pages = {89--98},
 	file = {PDF:/home/alex/Zotero/storage/JREACGRA/Wallach and Moghissi - 1980 - Prediction and Detection of Ovulation.pdf:application/pdf},
 }
+
+@misc{pham_dropout_2014,
+	title = {Dropout improves {Recurrent} {Neural} {Networks} for {Handwriting} {Recognition}},
+	url = {http://arxiv.org/abs/1312.4569},
+	doi = {10.48550/arXiv.1312.4569},
+	abstract = {Recurrent neural networks (RNNs) with Long Short-Term memory cells currently hold the best known results in unconstrained handwriting recognition. We show that their performance can be greatly improved using dropout - a recently proposed regularization method for deep architectures. While previous works showed that dropout gave superior performance in the context of convolutional networks, it had never been applied to RNNs. In our approach, dropout is carefully used in the network so that it does not affect the recurrent connections, hence the power of RNNs in modeling sequence is preserved. Extensive experiments on a broad range of handwritten databases confirm the effectiveness of dropout on deep architectures even when the network mainly consists of recurrent and shared connections.},
+	urldate = {2025-07-22},
+	publisher = {arXiv},
+	author = {Pham, Vu and Bluche, Théodore and Kermorvant, Christopher and Louradour, Jérôme},
+	month = mar,
+	year = {2014},
+	note = {arXiv:1312.4569 [cs]},
+	keywords = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Computer Science - Neural and Evolutionary Computing},
+	file = {Full Text PDF:/home/alex/Zotero/storage/IA52LNE8/Pham et al. - 2014 - Dropout improves Recurrent Neural Networks for Handwriting Recognition.pdf:application/pdf;Snapshot:/home/alex/Zotero/storage/LJ8EJ5PS/1312.html:text/html},
+}
+
+@article{wen_time_2023,
+	title = {Time {Series} {Prediction} {Based} on {LSTM}-{Attention}-{LSTM} {Model}},
+	volume = {11},
+	issn = {2169-3536},
+	url = {https://ieeexplore.ieee.org/document/10124729/},
+	doi = {10.1109/ACCESS.2023.3276628},
+	abstract = {Time series forecasting uses data from the past periods of time to predict future information, which is of great significance in many applications. Existing time series forecasting methods still have problems such as low accuracy when dealing with some non-stationary multivariate time series data forecasting. Aiming at the shortcomings of existing methods, in this paper we propose a new time series forecasting model LSTM-attention-LSTM. The model uses two LSTM models as the encoder and decoder, and introduces an attention mechanism between the encoder and decoder. The model has two distinctive features: first, by using the attention mechanism to calculate the interrelationship between sequence data, it overcomes the disadvantage of the coder-and-decoder model in that the decoder cannot obtain sufficiently long input sequences; second, it is suitable for sequence forecasting with long time steps. In this paper we validate the proposed model based on several real data sets, and the results show that the LSTM-attention-LSTM model is more accurate than some currently dominant models in prediction. The experiment also assessed the effect of the attention mechanism at different time steps by varying the time step.},
+	urldate = {2025-07-22},
+	journal = {IEEE Access},
+	author = {Wen, Xianyun and Li, Weibang},
+	year = {2023},
+	keywords = {attention mechanisms, Autoregressive processes, Data models, Decoding, encoder and decoder model, Forecasting, Logic gates, long short-term memory networks, Predictive models, Time series analysis, Time series forecasting},
+	pages = {48322--48331},
+	file = {Full Text PDF:/home/alex/Zotero/storage/3M54PVSE/Wen and Li - 2023 - Time Series Prediction Based on LSTM-Attention-LSTM Model.pdf:application/pdf},
+}
+
+@misc{goyal_accurate_2018,
+	title = {Accurate, {Large} {Minibatch} {SGD}: {Training} {ImageNet} in 1 {Hour}},
+	shorttitle = {Accurate, {Large} {Minibatch} {SGD}},
+	url = {http://arxiv.org/abs/1706.02677},
+	doi = {10.48550/arXiv.1706.02677},
+	abstract = {Deep learning thrives with large neural networks and large datasets. However, larger networks and larger datasets result in longer training times that impede research and development progress. Distributed synchronous SGD offers a potential solution to this problem by dividing SGD minibatches over a pool of parallel workers. Yet to make this scheme efficient, the per-worker workload must be large, which implies nontrivial growth in the SGD minibatch size. In this paper, we empirically show that on the ImageNet dataset large minibatches cause optimization difficulties, but when these are addressed the trained networks exhibit good generalization. Specifically, we show no loss of accuracy when training with large minibatch sizes up to 8192 images. To achieve this result, we adopt a hyper-parameter-free linear scaling rule for adjusting learning rates as a function of minibatch size and develop a new warmup scheme that overcomes optimization challenges early in training. With these simple techniques, our Caffe2-based system trains ResNet-50 with a minibatch size of 8192 on 256 GPUs in one hour, while matching small minibatch accuracy. Using commodity hardware, our implementation achieves {\textasciitilde}90\% scaling efficiency when moving from 8 to 256 GPUs. Our findings enable training visual recognition models on internet-scale data with high efficiency.},
+	urldate = {2025-07-22},
+	publisher = {arXiv},
+	author = {Goyal, Priya and Dollár, Piotr and Girshick, Ross and Noordhuis, Pieter and Wesolowski, Lukasz and Kyrola, Aapo and Tulloch, Andrew and Jia, Yangqing and He, Kaiming},
+	month = apr,
+	year = {2018},
+	note = {arXiv:1706.02677 [cs]},
+	keywords = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Machine Learning},
+	annote = {Comment: Tech report (v2: correct typos)},
+	file = {Full Text PDF:/home/alex/Zotero/storage/5MKPLWI7/Goyal et al. - 2018 - Accurate, Large Minibatch SGD Training ImageNet in 1 Hour.pdf:application/pdf;Snapshot:/home/alex/Zotero/storage/TRYJFLDW/1706.html:text/html},
+}