| 1. |
- Blom, Victoria, et al.
(författare)
-
Work–home interference and burnout in Swedish women and men : The importance of genetics and family environment
- 2013
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Genetic influences on perceived demands and burnout are shown in previous studies, suggesting genetic and shared environmental influences may underlie the associations between work–home interference and burnout. The present study sets out to increase the currently limited understanding of the biological and social correlates of work–home interference (WHI) by investigating whether WHI is related to burnout while taking sex, age, children, and genetic and shared environmental factors into account. A total of 13 730 individuals, including 2223 complete twin pairs, from the Swedish Twin Registry were included in the study. The effects of work–home conflict (WHC) and home–work conflict (HWC) on burnout between- and within-pairs were analyzed with Linear Mixed Models with and without stratification by sex. The results showed significant main effects of WHC and HWC on burnout and co-twin control analyses suggested that shared environmental factors may be involved in the association between HWC and burnout in women. As regards WHC and burnout, genetic or shared environmental factors did not seem to be involved. Adjustment for age and children did not change the results. The present study contributes with new knowledge of the mechanisms involved in the associations between work–home interference and burnout.
|
|
| 2. |
- Meding, Isak, et al.
(författare)
-
You can have your ensemble and run it too - Deep Ensembles Spread Over Time
- 2023
-
Ingår i: Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023. - : IEEE COMPUTER SOC. ; , s. 4022-4031
-
Konferensbidrag (refereegranskat)abstract
- Ensembles of independently trained deep neural networks yield uncertainty estimates that rival Bayesian networks in performance. They also offer sizable improvements in terms of predictive performance over single models. However, deep ensembles are not commonly used in environments with limited computational budget - such as autonomous driving - since the complexity grows linearly with the number of ensemble members. An important observation that can be made for robotics applications, such as autonomous driving, is that data is typically sequential. For instance, when an object is to be recognized, an autonomous vehicle typically observes a sequence of images, rather than a single image. This raises the question, could the deep ensemble be spread over time?In this work, we propose and analyze Deep Ensembles Spread Over Time (DESOT). The idea is to apply only a single ensemble member to each data point in the sequence, and fuse the predictions over a sequence of data points. We implement and experiment with DESOT for traffic sign classification, where sequences of tracked image patches are to be classified. We find that DESOT obtains the benefits of deep ensembles, in terms of predictive and uncertainty estimation performance, while avoiding the added computational cost. Moreover, DESOT is simple to implement and does not require sequences during training. Finally, we find that DESOT, like deep ensembles, outperform single models for out-of-distribution detection.
|
|
