With high dropout rates as observed in many current larger-scale online courses, mechanisms that are able to predict student dropout become increasingly important. While this problem is partially solved for students that are active in online forums, this is not yet the case for the more general student population. In this paper, we present an approach that works on click-stream data. Among other features, the machine learning algorithm takes the weekly history of student data into account and thus is able to notice changes in student behavior over time. In the later phases of a course (i.e., once such history data is available), this approach is able to predict dropout significantly better than baseline methods.

VAE requires the standard Gaussian distribution as a prior in the latent space. Since all codes tend to follow the same prior, it often suffers the so-called "posterior collapse". To avoid this, this paper introduces the class specific distribution for the latent code. But different from cVAE, we present a method for disentangling the latent space into the label relevant and irrelevant dimensions, z s and z u , for a single input. We apply two separated encoders to map the input into z s and z u respectively, and then give the concatenated code to the decoder to reconstruct the input. The label irrelevant code z u represent the common characteristics of all inputs, hence they are constrained by the standard Gaussian, and their encoder is trained in amortized variational inference way, like VAE. While z s is assumed to follow the Gaussian mixture distribution in which each component corresponds to a particular class. The parameters for the Gaussian components in z s encoder are optimized by the label supervision in a global stochastic way. In theory, we show that our method is actually equivalent to adding a KL divergence term on the joint distribution of z s and the class label c, and it can directly increase the mutual information between z s and the label c. Our model can also be extended to GAN by adding a discriminator in the pixel domain so that it produces high quality and diverse images. arXiv:1812.09502v4 [cs.CV] 15 Mar 2019 concat 5 × 5 conv, 32, stride 1, lrelu 5 × 5 conv, 64, stride 2, batchnorm, relu fc, 1024, batchnorm, relu 5 × 5 conv, 128, stride 2, lrelu 3 × 3 conv, 128, stride 2, batchnorm, relu 5 × 5 conv, 256, stride 2, batchnorm, relu 5 × 5 conv, 256, stride 2, lrelu 3 × 3 conv, 256, stride 2, batchnorm, relu 5 × 5 conv, 256, stride 1, batchnorm, relu 5 × 5 conv, 256, stride 2, lrelu fc, 1024, batchnorm, relu 5 × 5 conv, 128, stride 2, batchnorm, relu fc, 512, lrelu fc, 100 (for z s ) / 200 (for z u ) 5 × 5 conv, 64, stride 2, batchnorm, relu fc, 1 5 × 5 conv, 32, stride 2, batchnorm, relu 5 × 5 conv, 3, stride 1, tanh Table 3. The network structure for Cifar-10.Discriminator for FaceScrub input x ∈ R 64×64×3 3 × 3 conv, 64, stride 2, lrelu 3 × 3 conv, 128, stride 2, lrelu 3 × 3 conv, 256, stride 1, lrelu 3 × 3 conv, 256, stride 2, lrelu 3 × 3 conv, 512, stride 1, lrelu 3 × 3 conv, 512, stride 2, lrelu 3 × 3 conv, 512, stride 2, lrelu global average pooling fc, 1024, lrelu fc, 1 Table 4. The network structure of discriminator for FaceScrub.

Collaborative learning is an educational strategy which is popularly used in project-based courses in schools and colleges. The diversity of group members is frequently considered to be a crucial criterion that can promote intensive intra-group interaction and successful learning outcomes. Yet, when the number of students is up to several hundreds, it is challenging for instructors to look for an optimal group formation considering maximal diversity of students in every group. To address this problem, this paper presents a discrete particle swarm optimization approach to compose heterogeneous learning groups. We carried out simulations based on optimizing the heterogeneity of gender and personality type. The experimental results show that the proposed approach is an effective and stable method that can support instructors to compose heterogeneous collaborative learning groups.

No abstract

No abstract