Instructional Material
Supercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer
ECRT consistently outperforms the others, especially in the low-sample regime.
The MAGICAL Benchmark for Robust Imitation
The robot could learn from these demonstrations to complete the tasks autonomously. For IL algorithms to be useful, however, they must be able to learn how to perform tasks from few demonstrations. A domestic robot wouldn't be very helpful if it required thirty demonstrations before it figured out that you are deliberately washing your purple cravat
MetaTeacher: Coordinating Multi-Model Domain Adaptation for Medical Image Classification (Appendix) Zhenbin Wang 1, Mao Y e
We visualize the domain adaptation performance on the transfer scenario NIH-CXR14, CheXpert, MIMIC-CXR to Open-i . The visualization sample in the Open-i is suffering from Atelecsis and Effusion disease.
Mitigating Forgetting in Online Continual Learning via Instance-A ware Parameterization (Supplemental) Hung-Jen Chen
Encourage controller to search unseen blocks by Eq. 9 Get reward r by Eq. 3 We conduct an ablation study to show the strength of count-based search exploration. We compare the performance difference between InstAParam with and without count-based exploration. Although, InstaNAS tries to solve the problem with "policy shuffling", we found that it does not solve the problem in this scenario. The detailed accuracy is listed in Table 2. CIFAR-10 and does not sacrifice the initial performance. First, we will focus on the distribution of the policy for each task.
Autonomous Reinforcement Learning via Subgoal Curricula
Reinforcement learning (RL) promises to enable autonomous acquisition of complex behaviors for diverse agents.
Supplementary Material for " Training Over-parameterized Models with Non-decomposable Objectives " Algorithm 2 Reductions-based Algorithm for Constraining Coverage (2)
These algorithms additionally incorporate the "two dataset" trick suggested by Cotter et al. We will find the following standard result to be useful in our proofs. We reproduce the proof from Narasimhan et al. We provide a proof for Proposition 4 . The proof follows by setting D = G and applying Proposition 4 .
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning
Continual learning agents experience a stream of (related) tasks.
Calibrating CNNs for Lifelong Learning
We present an approach for lifelong/continual learning of convolutional neural networks (CNN) that does not suffer from the problem of catastrophic forgetting when moving from one task to the other. We show that the activation maps generated by the CNN trained on the old task can be calibrated using very few calibration parameters, to become relevant to the new task.