One-Shot Imitation Learning. Yan Duan et al. 2017

Summary Abstract Ideally, robots should be able to learn from very few demonstrations of any given task, and instantly generalize to new situations of the same task, without requiring task-specific engineering. In this paper, we propose a meta-learning framework for achieving such capability, which we call one-shot imitation learning. Task examples: to stack all blocks […]

Conditional Generative Adversarial Nets | M. Mirza, S. Osindero | 2014

Introduction Conditional version of Generative Adversarial Nets (GAN) where both generator and discriminator are conditioned on some data y (class label or data from some other modality). Architecture Feed y into both the generator and discriminator as additional input layers such that y and input are combined in a joint hidden representation.

Studying Generative Adversarial Networks (GANs)

References Lecture 13: Generative Models. CS231n: Convolutional Neural Networks for Visual Recognition. Spring 2017. [SLIDE][VIDEO] Generative Adversarial Nets. Goodfellow et al.. NIPS 2014. 2014. [LINK][arXiv] How to Train a GAN? Tips and tricks to make GANs work. Soumith Chintala. github. [LINK] The GAN Zoo. Avinash Hindupur. github. [LINK]

Lecture 2: Markov Decision Processes | Reinforcement Learning | David Silver | Course

1. Markov Process / Markov chain 1.1. Markov process A Markov process or Markov chain is a tuple such that is a finite set of states, and is a transition probability matrix. In a  Markov process, the initial state should be given. How do we choose the initial state is not a role of the Markov process. 1.2. State […]

Reinforcement Learning | David Silver | Course

Brief information Instructor: David Silver Course homepage: [LINK] Video lecture list: [LINK] Lecture schedule Lecture 1: Introduction to Reinforcement Learning Lecture 2: Markov Decision Processes Lecture 3: Planning by Dynamic Programming Lecture 4: Model-Free Prediction Lecture 5: Model-Free Control Lecture 6: Value Function Approximation Lecture 7: Policy Gradient Methods Lecture 8: Integrating Learning and Planning […]

Batch Normalization | Summary

References Sergey Ioffe, Christian Szegedy (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. ICML 2015. [ICML][arXiv] Lecture 6: Training Neural Networks, Part 1. CS231n:Convolutional Neural Networks for Visual Recognition. 48:52~1:04:39 [YouTube] Choung young jae (2017. 7. 2.). PR-021: Batch Normalization. Youtube. [YouTube] tf.nn.batch_normalization. Tensorflow. [LINK] Rui Shu (27 DEC 2016). A GENTLE […]

Convolutional Neural Networks | Study

  References L. Fei-Fei, Justin Johnson (Spring 2017)CS231n: Convolutional Neural Networks for Visual Recognition. [LINK] Jefkine (5 September 2016). Backpropagation In Convolutional Neural Networks. [LINK] Convnet: Implementing Convolution Layer with Numpy [LINK] CNN의 역전파(backpropagation) [LINK]

CS231n: Convolutional Neural Networks for Visual Recognition | Course

Lecture 6 | Training Neural Networks I Sigmoid Problems of the sigmoid activation function Problem 1: Saturated neurons kill the gradients. Problem 2: Sigmoid outputs are not zero-centered. Suppose a given feed-forward neural network has hidden layers and all activation functions are sigmoid. Then, except the first layer, the other layers get only positive inputs. […]

Sequence to Sequence Learning with Neural Networks | Summary

References Ilya Sutskever, Oriol Vinyals, Quoc V. Le (2014). “Sequence to Sequence Learning with Neural Networks”. NIPS 2014: 3104-3112. [PDF] Sequence-to-Sequence Models. TensorFlow [LINK] The official tutorial for sequence-to-sequence models. Seq2seq Library (contrib). Tensorflow [LINK] Translation with a Sequence to Sequence Network and Attention. PyTorch. [LINK]