The LSTM, feeding by image-sentence pairs sequentially in the training stage, is trained to maximize the joint probability of target word in each time step.
Images, sentences, even whole scenes of the novel are recycled from that book and from her collections of short fiction.
These data were analysed as before using a repeated-measure ANOVA having within-participant factors of Source (images, sentences or pictures) and Valence (negative or benign).
"Figure 1 (major): I feel that the info provided by points C and D is trivial, whilst point A's images, sentences and legends can be improved.
Mean affective ratings were first entered into a repeated-measure analysis of variance (ANOVA) having within-participant factors of Source (images, sentences or pictures) and Emotional Valence (negative or benign).
Methods 2 nd Par, Line 5 (minor): "Maximising" is used, but probably the meaning is "increasing" (the number of). Figure 1 (major): I feel that the info provided by points C and D is trivial, whilst point A's images, sentences and legends can be improved.
A repeated-measure ANOVA of false alarm rates, having within-participant factors of Source (images, sentences or new) and Valence (negative or benign) revealed significant main effects of both Source, F 2, 100) = 35.19, p <.001, ηp =.41; and Valence, F 1, 50) = 5.53, p <.03, ηp =.10.
Setting a reasonable minimum can be more useful for experimental design than saying the larger the sample size the most robust the result. 2 nd Par, Line 5 (minor): "Maximising" is used, but probably the meaning is "increasing" (the number of). Figure 1 (major): I feel that the info provided by points C and D is trivial, whilst point A's images, sentences and legends can be improved.
In a planned comparison of image and sentence trials, images were more likely to be misattributed than sentences, F 1, 50) = 5.65, p <.03, ηp =.10.
The three previously used sets of captions were reassigned to image trials, sentence trials, or appeared for the first time in the questionnaire, with set assignment counterbalanced across participants.
