Testing function diagram of QIMPN-PCA-DC. by Jun Zhao (59250)

Algorithm of the brightness scale calibration experiment. by Krzysztof Petelczyc (3954203)

“…<p>In the algorithm, the following variables were used: “I” denotes the current luminous intensity of the reference diode, “inc” denotes the current difference between reference and target diode luminous intensity; “cnt” is the current number of performed trials, while “correct” is a counter of correct answers in cnt trials, both of them are counted separately for every settings of I and inc. …”

Reconstructing <i>sparse</i>, binary patterns using message passing algorithms and PCA. by Sebastian Goldt (14522594)

“…<p>We plot the mse per pattern obtained by the AMP algorithm, <a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1010813#pcbi.1010813.e072" target="_blank">Eq (32)</a>, as a function of the effective noise Δ (<a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1010813#pcbi.1010813.e032" target="_blank">9</a>), for random (<a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1010813#pcbi.1010813.e044" target="_blank">15</a>) and informed (<a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1010813#pcbi.1010813.e045" target="_blank">16</a>) initialisations. …”

Functional PCA With Covariate-Dependent Mean and Covariance Structure by Fei Ding (134577)

“…<p>Incorporating covariates into functional principal component analysis (PCA) can substantially improve the representation efficiency of the principal components and predictive performance. …”

Loss functions between PCA-DNN model and PCA-LSTM model. by Cihun-Siyong Alex Gong (11874066)

Explained variance ration of the PCA algorithm. by Abeer Aljohani (18497914)

Damping oscillation function (before adding random numbers). by Fujun Wang (96184)

Performance of PCA and Joint Autoencoder (JAE) denoising algorithms. by Ege Altan (11768156)

The loss function of network structures, LPC-DNN, LPC-PCA-DNN, LPC-LSTM, LPC-PCA-LSTM, MFCC-DNN, MFCC-PCA-DNN, MFCC-LSTM and MFCC-PCA-LSTM, as the epoch increases. by Cihun-Siyong Alex Gong (11874066)

The comparison of TL before and after optimization. by Shangyang Jin (21772466)

The comparison of TL before and after optimization. by Shangyang Jin (21772466)

Comparison of loss function curves before and after improvement. by Xiaozhou Feng (2918222)

Application of the algorithm to unseen data. Presynaptic neurons labelled by rabies viral injection into layer 2/3 primary visual cortex in Penk-Cre mice. by Adam L. Tyson (10892822)

The losses of the training process before and after the optimization of loss function. by Peihan Wen (6324315)

Network propagation improves the correlation between mRNA and protein levels of ageing tissues (brain and liver) and PCa samples. by Konstantina Charmpi (9901053)

Path comparison before and after smoothing. by Zhenggang Wang (1753657)

Comparison before and after path pruning. by Zhenggang Wang (1753657)

Loss function value changes in CNN training changes with epochs for both training dataset and testing dataset. by Jiaxi Wang (545353)

Improved SHA256 algorithm operation diagram. by Su Li (294188)

Functions of genes, detected simultaneously in 3 "diseased" blocks («Prostate Disease», «PCa», «Not PCa») and missing in the "Healthy" block and one gene (HRAS), found only in the... by O. E. Bryzgunova (6577043)