Policy distillation, which transfers a teacher policy to a student policy has achieved great success in challenging tasks of deep reinforcement learning. This teacher-student framework requires a well-trained teacher model which is computationally expensive. Moreover, the performance of the student model could be limited by the teacher model if the teacher model is not optimal. In the light of collaborative learning, we study the feasibility of involving joint intellectual efforts from diverse perspectives of student models. In this work, we introduce dual policy distillation(DPD), a student-student framework in which two learners operate on the same environment to explore different perspectives of the environment and extract knowledge from each other to enhance their learning. The key challenge in developing this dual learning framework is to identify the beneficial knowledge from the peer learner for contemporary learning-based reinforcement learning algorithms, since it is unclear whether the knowledge distilled from an imperfect and noisy peer learner would be helpful. To address the challenge, we theoretically justify that distilling knowledge from a peer learner will lead to policy improvement and propose a disadvantageous distillation strategy based on the theoretical results. The conducted experiments on several continuous control tasks show that the proposed framework achieves superior performance with a learning-based agent and function approximation without the use of expensive teacher models.

The extrapolation strategy raised by Nesterov, which can accelerate the convergence rate of gradient descent methods by orders of magnitude when dealing with smooth convex objective, has led to tremendous success in training machine learning tasks. In this article, the convergence of individual iterates of projected subgradient (PSG) methods for nonsmooth convex optimization problems is theoretically studied based on Nesterov's extrapolation, which we name individual convergence. We prove that Nesterov's extrapolation has the strength to make the individual convergence of PSG optimal for nonsmooth problems. In light of this consideration, a direct modification of the subgradient evaluation suffices to achieve optimal individual convergence for strongly convex problems, which can be regarded as making an interesting step toward the open question about stochastic gradient descent (SGD) posed by Shamir. Furthermore, we give an extension of the derived algorithms to solve regularized learning tasks with nonsmooth losses in stochastic settings. Compared with other state-of-the-art nonsmooth methods, the derived algorithms can serve as an alternative to the basic SGD especially in coping with machine learning problems, where an individual output is needed to guarantee the regularization structure while keeping an optimal rate of convergence. Typically, our method is applicable as an efficient tool for solving large-scale $l$1-regularized hinge-loss learning problems. Several comparison experiments demonstrate that our individual output not only achieves an optimal convergence rate but also guarantees better sparsity than the averaged solution.

Mining and learning the shape variability of underlying population has benefited the applications including parametric shape modeling, 3D animation, and image segmentation. The current statistical shape modeling method works well on learning unstructured shape variations without obvious pose changes (relative rotations of the body parts). Studying the pose variations within a shape population involves segmenting the shapes into different articulated parts and learning the transformations of the segmented parts. This paper formulates the pose learning problem as mixtures of factor analyzers. The segmentation is obtained by components posterior probabilities and the rotations in pose variations are learned by the factor loading matrices. To guarantee that the factor loading matrices are composed by rotation matrices, constraints are imposed and the corresponding closed form optimal solution is derived. Based on the proposed method, the pose variations are automatically learned from the given shape populations. The method is applied in motion animation where new poses are generated by interpolating the existing poses in the training set. The obtained results are smooth and realistic.

We describe our submission to the 2020 Duolingo Shared Task on Simultaneous Translation And Paraphrase for Language Education (STAPLE) (Mayhew et al., 2020). We view MT models at various training stages (i.e., checkpoints) as human learners at different levels. Hence, we employ an ensemble of multi-checkpoints from the same model to generate translation sequences with various levels of fluency. From each checkpoint, for our best model, we sample n-Best sequences (n=10) with a beam width =100. We achieve 37.57 macro F1 with a 6 checkpoint model ensemble on the official English to Portuguese shared task test data, outperforming a baseline Amazon translation system of 21.30 macro F1 and ultimately demonstrating the utility of our intuitive method.

Gain a Strong Understanding of TensorFlow - Google's Cutting-Edge Deep Learning Framework Build Deep Learning Algorithms from Scratch in Python Using NumPy and TensorFlow Set Yourself Apart with Hands-on Deep and Machine Learning Experience Grasp the Mathematics Behind Deep Learning Algorithms Understand Backpropagation, Stochastic Gradient Descent, Batching, Momentum, and Learning Rate Schedules Know the Ins and Outs of Underfitting, Overfitting, Training, Validation, Testing, Early Stopping, and Initialization Competently Carry Out Pre-Processing, Standardization, Normalization, and One-Hot Encoding Description Gain a Strong Understanding of TensorFlow - Google's Cutting-Edge Deep Learning Framework Build Deep Learning Algorithms from Scratch in Python Using NumPy and TensorFlow Set Yourself Apart with Hands-on Deep and Machine Learning Experience Grasp the Mathematics Behind Deep Learning Algorithms Understand Backpropagation, Stochastic Gradient Descent, Batching, Momentum, and Learning Rate Schedules Know the Ins and Outs of Underfitting, Overfitting, Training, Validation, Testing, Early Stopping, and Initialization Competently Carry Out Pre-Processing, Standardization, Normalization, and One-Hot Encoding Data scientists, machine learning engineers, and AI researchers all have their own skillsets. But what is that one special thing they have in common? They are all masters of deep learning. We often hear about AI, or self-driving cars, or the'algorithmic magic' at Google, Facebook, and Amazon. But it is not magic - it is deep learning. And more specifically, it is usually deep neural networks – the one algorithm to rule them all.

Digital generated image of data. When it comes to AI, much of the attention has been on deep learning. This part of the AI world has seen great strides, such as with image recognition. But of course, there are other areas of AI that look promising, such as reinforcement learning. Keep in mind that cutting-edge companies like Google's DeepMind and OpenAI have already made breakthroughs with this approach.

Kennisnet Technology Compass 2019-2020, y que comienza así: Please note: This report is written from a Dutch perspective and with the Dutch educational system and its structure in mind. Please take this into account when reading this report. What will you find in this technology compass? If someone had told you 25 years ago – roughly at the time the internet started to rise – that in 2019, you would be swiping on your smartphone for multiple hours a day, and that thanks to the internet you'd know exactly what time your aunt in France was drinking her latte, or that teenagers could become drone pilots during their vocational studies, would you have believed that person? Probably not, as nobody can predict the future.

Policy evaluation algorithms are essential to reinforcement learning due to their ability to predict the performance of a policy. However, there are two long-standing issues lying in this prediction problem that need to be tackled: off-policy stability and on-policy efficiency. The conventional temporal difference (TD) algorithm is known to perform very well in the on-policy setting, yet is not off-policy stable. On the other hand, the gradient TD and emphatic TD algorithms are off-policy stable, but are not on-policy efficient. This paper introduces novel algorithms that are both off-policy stable and on-policy efficient by using the oblique projection method. The empirical experimental results on various domains validate the effectiveness of the proposed approach.

Early prediction of students at risk (STAR) is an effective and significant means to provide timely intervention for dropout and suicide. Existing works mostly rely on either online or offline learning behaviors which are not comprehensive enough to capture the whole learning processes and lead to unsatisfying prediction performance. We propose a novel algorithm (EPARS) that could early predict STAR in a semester by modeling online and offline learning behaviors. The online behaviors come from the log of activities when students use the online learning management system. The offline behaviors derive from the check-in records of the library. Our main observations are two folds. Significantly different from good students, STAR barely have regular and clear study routines. We devised a multi-scale bag-of-regularity method to extract the regularity of learning behaviors that is robust to sparse data. Second, friends of STAR are more likely to be at risk. We constructed a co-occurrence network to approximate the underlying social network and encode the social homophily as features through network embedding. To validate the proposed algorithm, extensive experiments have been conducted among an Asian university with 15,503 undergraduate students. The results indicate EPARS outperforms baselines by 14.62% ~ 38.22% in predicting STAR.

Designing resource-efficient Deep Neural Networks (DNNs) is critical to deploy deep learning solutions over edge platforms due to diverse performance, power, and memory budgets. Unfortunately, it is often the case a well-trained ML model does not fit to the constraint of deploying edge platforms, causing a long iteration of model reduction and retraining process. Moreover, a ML model optimized for platform-A often may not be suitable when we deploy it on another platform-B, causing another iteration of model retraining. We propose a conditional neural architecture search method using GAN, which produces feasible ML models for different platforms. We present a new workflow to generate constraint-optimized DNN models. This is the first work of bringing in condition and adversarial technique into Neural Architecture Search domain. We verify the method with regression problems and classification on CIFAR-10. The proposed workflow can successfully generate resource-optimized MLP or CNN-based networks.