### Table 4. Face Pose Estimation Accuracy

### Table 1: The classification results for gaze estima- tion with 100 testing gaze samples under different face poses for a person whose data is included in the training set.

2002

Cited by 18

### Table 4.2 shows the error rates for various sample size. 500 examples per view are finally adopted to compose Set 1 to balance the tradeoff.

"... In PAGE 5: ...06 84.56 Table4 . Face Pose Estimation Accuracy distribution of data points is highly nonlinear and complex, to a lower dimensional space in which the distribution be- comes simpler, tighter and therefore more predictable for better modeling of faces.... ..."

### Table 1: The terms used in the multitask learning procedure

### Table 1: Categorization of Manifold Learning Methods

2007

"... In PAGE 2: ...Table 1: Categorization of Manifold Learning Methods 2 Manifold Learning Methods and their connections to Distance Metric Learning Manifold Learning approaches can be categorized along the following two dimensions: first, the learnt embedding is linear or nonlinear; and second, the structure to be pre- served is global or local (see Table1 ). Based on the analysis in section 1, all the linear methods in Table 1 except Multidimensional Scaling (MDS), learn an explicit linear projective mapping and can be interpreted as the problem of distance metric learning.... In PAGE 2: ...Table 1: Categorization of Manifold Learning Methods 2 Manifold Learning Methods and their connections to Distance Metric Learning Manifold Learning approaches can be categorized along the following two dimensions: first, the learnt embedding is linear or nonlinear; and second, the structure to be pre- served is global or local (see Table 1). Based on the analysis in section 1, all the linear methods in Table1 except Multidimensional Scaling (MDS), learn an explicit linear projective mapping and can be interpreted as the problem of distance metric learning. MDS finds the low-rank projection that best preserves the inter-point distance matrix E.... ..."

### Table 2. Deep Learning Differences by Discipline

2005

"... In PAGE 12: ... In fact, many seniors in every area use deep learning approaches at least some of the time. For the deep learning scale ( Table2 ), seniors in the social sciences have the highest average score even after controlling for student characteristics (effect size with controls = 0.26, p lt; 0.... ..."

### Table 4. Error rates of multi-task learning. Task Error Rate (%)

2007

"... In PAGE 32: ... A total of 2,000 samples, not including all the samplesb learned by task 1, is sufficient for task 2, because layer-1 has already taken into account a large amount of variations learned for task 1. Table4 shows the error rates of multi-task learning. Again, the main purpose is not to show the absolute performance, but rather the effects of multi-task learning by such a network.... ..."

### Table 1: Contemporary learning strategies supporting deep approaches to learning

2002

"... In PAGE 2: ...mphasis on student-centred instruction (p. 45). Many writers have attempted to conceptualise the attributes and nature of learning settings for higher education that promote deep learning through an emphasis on learning processes. Table1 provides a summary and synthesis of the descriptions of a number of researchers and writers who have explored these conditions. A Framework Describing Learning Approaches A number of consistent elements appear to emerge from the literature which describes the conditions under which students can be encouraged to seek understanding and comprehension as distinct from surface level learning in instances where generic skills development is being sought.... ..."

Cited by 1

### Table 2: Explained variance for the school data and the newspaper data. The evaluated methods are sin- gle task learning (STL), maximum likelihood multitask learning (ML MTL), Bayesian multitask learning, task clustering with two clusters and task gating with two clusters.

2003

"... In PAGE 7: ... We applied single task learning, non-Bayesian and Bayesian multitask learning on the school data. The results are expressed in Table2 . Single task learning explained 9.... ..."

Cited by 24

### Table 2: Explained variance for the school data and the newspaper data. The evaluated methods are sin- gle task learning (STL), maximum likelihood multitask learning (ML MTL), Bayesian multitask learning, task clustering with two clusters and task gating with two clusters.

2003

"... In PAGE 7: ... We applied single task learning, non-Bayesian and Bayesian multitask learning on the school data. The results are expressed in Table2 . Single task learning explained 9.... ..."

Cited by 24