Decrease in loss during the training process. by Muhammad Idrees (92773)

Selection frequencies plotted in decreasing order. by Hannah P. Rowe (7830599)

Tissue, days post-infection (dpi) and the top 10 most significant genes with increased and decreased expression with valid gene symbols for the response contrasts. by Gillian P. McHugo (8965919)

Accuracy of multiple classifiers with a deep-learning-based feature set by Afira Aslam (21433666)

Subjects:

Regression analyses of the number of all ultrasonic calls identified by the experienced researcher (A.P.; “Human”) and by the DeepSqueak machine learning tool. by Piotr Popik (292215)

Subjects:

Deep learning-based locomotive syndrome prediction method. by Junichi Kushioka (12236447)

Subjects:

Deep reinforcement learning process. by Sen Cao (6017846)

“…Experimental evaluations underscore the model’s distinct advantages, including a 26.9% reduction in vehicle-pedestrian conflicts, a 31.83% decrease in queue lengths, a 32.52% reduction in delays compared to fixed-time strategies, and a 35.17% reduction in pedestrian crossing wait times. …”

A frame from the video with behaviors annotated in a custom way. by Piotr Popik (292215)

Subjects:

A raw video analyzed by DLC shows the camera view with two white rats, a water supply at the bottom, a sandpaper and echo-attenuating sponge on the inner walls. by Piotr Popik (292215)

Subjects:

Evaluation of the effectiveness of double task. by Fan Yang (1413)

Subjects:

Evaluation of the effectiveness of pruning. by Fan Yang (1413)

Subjects:

The summary of ablation experiment. by Fan Yang (1413)

Subjects:

Schematic of SADBIFB. by Fan Yang (1413)

Subjects:

Schematic of the residual attention block. by Fan Yang (1413)

Subjects:

The structure of the proposed network. by Fan Yang (1413)

Subjects:

Predicted results of the TCCT [4] network. by Fan Yang (1413)

Subjects:

Visualized results of different boundary labels. by Fan Yang (1413)

Subjects:

A frame showing human annotations (+) and how accurately DLC recognized them (.). by Piotr Popik (292215)

Subjects:

Trust change by gender. by Alain Abi-Rizk (8549358)

Subjects:

Trust change by age group. by Alain Abi-Rizk (8549358)

Subjects: