Jeremy Howard jph00

## keras_raw-xception-149.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                jph00
                / keras_raw-xception-149.ipynb
            
            
              Created
              August 12, 2017 18:24
            
              
                nbs/keras_raw-xception-149.ipynb
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## index.html
<!DOCTYPE html>
<html>
<head><title>Brundage Bot Backfill</title></head>
<body>
<ul>
<li><a href="http://arxiv.org/abs/1710.00814">Detecting Adversarial Attacks on Neural Network Policies with Visual   Foresight</a>: Deep reinforcement learning has shown promising results in learning control policies for complex sequential decision-making tasks. However, these neural network-based policies are known to be vulnerable to adversarial examples. This vulnerability poses a potentially serious threat to safety-critical systems such as autonomous vehicles. In this paper, we propose a defense mechanism to defend reinforcement learning agents from adversarial attacks by leveraging an action-conditioned frame prediction module. Our core idea is that the adversarial examples targeting at a neural network-based policy are not effective for the frame prediction model. By comparing the action distribution produced by a policy from processing the current observed frame to the action distribution produced by the same policy f

## yolov3 config.txt
[convolutional] batch_normalize=1 filters=32 size=3 stride=1 pad=1 activation=leaky

# Downsample
[convolutional] batch_normalize=1 filters=64 size=3 stride=2 pad=1 activation=leaky
[convolutional] batch_normalize=1 filters=32 size=1 stride=1 pad=1 activation=leaky
[convolutional] batch_normalize=1 filters=64 size=3 stride=1 pad=1 activation=leaky
[shortcut] from=-3 activation=linear

# Downsample
[convolutional] batch_normalize=1 filters=128 size=3 stride=2 pad=1 activation=leaky

## fastai_cla.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                jph00
                / fastai_cla.md
            
            
              Last active
              July 10, 2018 17:58
            
          
    fast.ai Individual Contributor License Agreement

Thank you for your interest in contributing to open source software projects (“Projects”) made available by fast.ai, Inc or its affiliates (“Company”). This Individual Contributor License Agreement (“Agreement”) sets out the terms governing any source code, object code, bug fixes, configuration changes, tools, specifications, documentation, data, materials, feedback, information or other works of authorship that you submit or have submitted, in any form and in any manner, to Company in respect of any of the Projects (collectively “Contributions”). If you have any questions respecting this Agreement, please contact info@fast.ai.
You agree that the following terms apply to all of your past, present and future Contributions. Except for the licenses granted in this Agreement, you retain all of your right, title and interest in and to your Contributions.
Copyright License. You hereby grant, and agree to grant, to Company a non-exclusive, perpetual, irrevo

  
## install_basic.sh
sudo add-apt-repository -y ppa:apt-fast/stable
sudo add-apt-repository -y ppa:graphics-drivers/ppa
sudo apt-get update
sudo apt-get -y install apt-fast
# prompts

sudo apt-fast -y upgrade

sudo apt-fast install -y ubuntu-drivers-common libvorbis-dev libflac-dev libsndfile-dev cmake build-essential libgflags-dev libgoogle-glog-dev libgtest-dev google-mock zlib1g-dev libeigen3-dev libboost-all-dev libasound2-dev libogg-dev libtool libfftw3-dev libbz2-dev liblzma-dev libgoogle-glog0v5 gcc-6 gfortran-6 g++-6 doxygen graphviz libsox-fmt-all parallel exuberant-ctags vim-nox python-powerline python3-pip
sudo apt-fast install -y tigervnc-standalone-server firefox lsyncd mesa-common-dev ack

## install_basic.sh
sudo add-apt-repository -y ppa:apt-fast/stable
sudo add-apt-repository -y ppa:graphics-drivers/ppa
sudo apt-get update
sudo apt-get -y install apt-fast
# prompts

sudo apt-fast -y upgrade

sudo apt-fast install -y ubuntu-drivers-common libvorbis-dev libflac-dev libsndfile-dev cmake build-essential libgflags-dev libgoogle-glog-dev libgtest-dev google-mock zlib1g-dev libeigen3-dev libboost-all-dev libasound2-dev libogg-dev libtool libfftw3-dev libbz2-dev liblzma-dev libgoogle-glog0v5 gcc-6 gfortran-6 g++-6 doxygen graphviz libsox-fmt-all parallel exuberant-ctags vim-nox python-powerline python3-pip
sudo apt-fast install -y tigervnc-standalone-server firefox lsyncd mesa-common-dev ack

## keras_raw-vgg16.ipynb

      
              1 file
            
          
              1 fork
            
          
              0 comments
            
          
              1 star
            
          
                jph00
                / keras_raw-vgg16.ipynb
            
            
              Created
              August 13, 2017 14:42
            
              
                nbs/keras_raw-vgg16.ipynb
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## keras_raw-xception-149.ipynb

      
              1 file
            
          
              1 fork
            
          
              0 comments
            
          
              1 star
            
          
                jph00
                / keras_raw-xception-149.ipynb
            
            
              Created
              August 13, 2017 01:58
            
              
                nbs/keras_raw-xception-149.ipynb
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## mit-letter.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              1 star
            
          
                jph00
                / mit-letter.md
            
            
              Last active
              September 8, 2019 15:17
            
          
    Dear Joi Ito, Reid Hoffman, Eileen Donahoe, David Hornik, Jennifer Lerner, James Manyika, Martha Minow, Amanda Nguyen, Laurene Powell Jobs, Jamila Raqib, Maria Zuber, and other fellow Selection Committee members for the MIT Disobedience Awards:
I was stunned and dismayed by Joi's email disclosing his extensive involvement, personally and through MIT, with Jeffrey Epstein. It is even harder to understand how this relationship could have begun and burgeoned in 2013, years after Epstein pled guilty to sex charges involving minor children. And it boggles the mind that this involvement spanned Epstein-tainted donations to MIT as well as investments in Joi's personal funds.
I'm struggling to find a way to make sense of this situation that does not lead me to write the sentence "Respected tech and academic leader raised money from convicted pedophile and leveraged that institutional connection to personally profit from the relationship." I am not trying to be unkind, but I would need help to understand why this se

  
## Genomics ideas.md

      
              1 file
            
          
              2 forks
            
          
              0 comments
            
          
              2 stars
            
          
                jph00
                / Genomics ideas.md
            
            
              Created
              May 16, 2018 17:55
            
          
    (from @philippbayer)
1. Gene function prediction - given a predicted protein or gene sequence, what is the function?

The classic approach is to use something like BLAST to compare with known sequences, but this has many drawbacks.
For starters, in plants the databases lean very heavily towards Arabidopsis thaliana, not more common plants such as maize or wheat.
People do get around this by looking for protein domains (Hidden Markov Models) but that doesn't go very far either,
you have to describe domains first, and many are very generic.
Can we classify protein/gene sequence using RNN/CNNs? Here's an example where someone tried
	<!DOCTYPE html>
	<html>
	<head><title>Brundage Bot Backfill</title></head>
	<body>
	<ul>
	<li><a href="http://arxiv.org/abs/1710.00814">Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight</a>: Deep reinforcement learning has shown promising results in learning control policies for complex sequential decision-making tasks. However, these neural network-based policies are known to be vulnerable to adversarial examples. This vulnerability poses a potentially serious threat to safety-critical systems such as autonomous vehicles. In this paper, we propose a defense mechanism to defend reinforcement learning agents from adversarial attacks by leveraging an action-conditioned frame prediction module. Our core idea is that the adversarial examples targeting at a neural network-based policy are not effective for the frame prediction model. By comparing the action distribution produced by a policy from processing the current observed frame to the action distribution produced by the same policy f
	[convolutional] batch_normalize=1 filters=32 size=3 stride=1 pad=1 activation=leaky

	# Downsample
	[convolutional] batch_normalize=1 filters=64 size=3 stride=2 pad=1 activation=leaky
	[convolutional] batch_normalize=1 filters=32 size=1 stride=1 pad=1 activation=leaky
	[convolutional] batch_normalize=1 filters=64 size=3 stride=1 pad=1 activation=leaky
	[shortcut] from=-3 activation=linear

	# Downsample
	[convolutional] batch_normalize=1 filters=128 size=3 stride=2 pad=1 activation=leaky
	sudo add-apt-repository -y ppa:apt-fast/stable
	sudo add-apt-repository -y ppa:graphics-drivers/ppa
	sudo apt-get update
	sudo apt-get -y install apt-fast
	# prompts

	sudo apt-fast -y upgrade

	sudo apt-fast install -y ubuntu-drivers-common libvorbis-dev libflac-dev libsndfile-dev cmake build-essential libgflags-dev libgoogle-glog-dev libgtest-dev google-mock zlib1g-dev libeigen3-dev libboost-all-dev libasound2-dev libogg-dev libtool libfftw3-dev libbz2-dev liblzma-dev libgoogle-glog0v5 gcc-6 gfortran-6 g++-6 doxygen graphviz libsox-fmt-all parallel exuberant-ctags vim-nox python-powerline python3-pip
	sudo apt-fast install -y tigervnc-standalone-server firefox lsyncd mesa-common-dev ack