harshraj22

• 1x1 convolutions have been extensively used to reduce the number of parameters without affecting the results much
• Deep Mutual Learning: Unlike bagging/ boosting, models learn jointly, and help each other to fit well
• Skip connections: Help solving degradation problem without adding parameters.
• Hard Sample Mining

diogofurtado

Disclaimer

I take no responsability for any problems a user might have on following this gist. This includes university problems.

The motivation for this is to document, as dummy-oriented as possible, a way to setup and add a system call to Minix OS. This is a classic assignment at Operational Systems classes (and is pretty cool tbh)

Configuration:

ISO used: minix_R3.3.0-588a35b.iso

karpathy

""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
import numpy as np
import cPickle as pickle
import gym

# hyperparameters
H = 200 # number of hidden layer neurons
batch_size = 10 # every how many episodes to do a param update?
learning_rate = 1e-4
gamma = 0.99 # discount factor for reward

NTag

Installation

1. Install Atom on your computer (https://atom.io)

2. Launch Atom, go in Preferences, then chose Install, search for "remote-atom", and install it

3. On the distant machine:

   cd ~
   wget https://raw.githubusercontent.com/aurora/rmate/master/rmate
   chmod +x rmate