Jerry Zhi-Yang He hzyjerry

NIPS Notes

Tutorials

Variational Inference

Simple Intro by Blei mostly going over review paper of Jordan
Later introduce SVI (Stochastic VI) as a remedy to solve VI tractably with large dataset.
Review the black box inference -assumption free VI- http://www.jmlr.org/proceedings/papers/v33/ranganath14.pdf
Key idea is replacing gradient and the expectation in VI formulation. Since expectation reqiuires exponential family assumption to work replacing expectation and gradient solves this if overall method is stochastic since your samples are unbiased gradient estimates satisfying Robinson-Monroe conditions however the variance is very large and it requires even further tricks

How to install Ubuntu 14.04.05 on Alienware 15 R3

Tiny guide to install Ubuntu 14.04.05 on a brand new Alienware 15 R3.

Let windows 10 install

Just next, next, next filling up your data.

You should get a BIOS update alert from the Alienware Update widget. If not, right click on the Down arrow icon in the bottom right extra icons ^ thing and right click, then click Check for Updates.

Simple automated GIT Deployment using GIT Hooks

Here are the simple steps needed to create a deployment from your local GIT repository to a server based on this in-depth tutorial.

How it works

You are developing in a working-copy on your local machine, lets say on the master branch. Most of the time, people would push code to a remote server like github.com or gitlab.com and pull or export it to a production server. Or you use a service like deepl.io to act upon a Web-Hook that's triggered that service.

In this article, I will share some of my experience on installing NVIDIA driver and CUDA on Linux OS. Here I mainly use Ubuntu as example. Comments for CentOS/Fedora are also provided as much as I can.

-ss 14:55 gives the timestamp where I want FFmpeg to start, as a duration string.
-t 5 says how much I want FFmpeg to decode, using the same duration syntax as for -ss.
-s 480x270 tells FFmpeg to resize the video output to 480 by 270 pixels.
-f image2 selects the output format, a series of still images — make sure there are leading zeros in filename.

	import torch
	import torch.nn.functional as F


	def maml_grad(model, inputs, outputs, lr, batch=1):
	"""
	Update a model's gradient using MAML.

	The gradient will point in the direction that
	improves the total loss across all inner-loop

	# to be used in conjunction with the functions defined here:
	# https://colab.research.google.com/github/tensorflow/hub/blob/master/examples/colab/biggan_generation_with_tf_hub.ipynb

	# party parrot transformation
	noise_seed_A = 3 # right facing
	noise_seed_B = 31 # left facing

	num_interps = 14
	truncation = 0.2
	category = 14

	import torch
	from torch import LongTensor
	from torch.nn import Embedding, LSTM
	from torch.autograd import Variable
	from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence

	## We want to run LSTM on a batch of 3 character sequences ['long_str', 'tiny', 'medium']
	#
	# Step 1: Construct Vocabulary
	# Step 2: Load indexed data (list of instances, where each instance is list of character indices)

	# Download installers
	mkdir ~/Downloads/nvidia
	cd ~/Downloads/nvidia
	wget https://developer.nvidia.com/compute/cuda/8.0/Prod2/local_installers/cuda_8.0.61_375.26_linux-run
	wget http://us.download.nvidia.com/XFree86/Linux-x86_64/384.59/NVIDIA-Linux-x86_64-384.59.run
	sudo chmod +x NVIDIA-Linux-x86_64-384.59.run
	sudo chmod +x cuda_8.0.61_375.26_linux-run
	./cuda_8.0.61_375.26_linux-run -extract=~/Downloads/nvidia/
	# Uninstall old stuff
	sudo apt-get --purge remove nvidia-*