0bserver07

Keybase proof

I hereby claim:

• I am 0bserver07 on github.
• I am yad (https://keybase.io/yad) on keybase.
• I have a public key whose fingerprint is C9E6 2E90 35FB 2FBF DBEC DCD4 AF6B BAD6 11DB BFBF

To claim this, I am signing this object:

0bserver07

{
    "loss": {
        "desc": null,
        "value": "cosine"
    },
    "seed": {
        "desc": null,
        "value": 0
    },
    "_wandb": {

0bserver07

git ls-remote origin 'pull/*/head' | awk '{print $2}' |
while read ref; do
  pr=$(echo $ref | cut -d/ -f3)
  git fetch origin $ref > /dev/null
  files_changed=$(git show --pretty=format:'' --name-only FETCH_HEAD|wc -l)
  author_files_changed=$(git log --pretty=format:"%an" -1)
  echo "PR number $pr has changes in $files_changed files by $author_files_changed"
done

0bserver07

# Inspired by http://liuhongjiang.github.io/hexotech/2015/10/14/alembic-support-multiple-model-files/

def combine_metadata():
    from sqlalchemy import MetaData
    import models  # models file into which all models are imported

    model_classes = []
    for model_name in models.__all__:
        model_classes.append(getattr(models, model_name))

0bserver07

0bserver07

error: "Faied to connect to the Docker daemon"

make sure to:

sudo su -
service docker start
docker images

0bserver07

Remove white background color of an image in ImageMagick

$ convert  your.jpg  -transparent white  your.png

Flatten a transparent image with a white background:

0bserver07

¹

<sup id="a1">[1](#f1)</sup>

1↩

<b id="f1">1</b>[↩](#a1)

0bserver07

{ "name":"component/adapters", "color":"bfd4f2"}, 
{ "name":"component/config", "color":"bfd4f2"},
{  "name":"component/documentation", "color":"bfd4f2"},
{"name":"component/extensions", "color":"bfd4f2"},
{ "name":"component/handlers", "color":"bfd4f2"}, 
{"name":"component/http", "color":"bfd4f2"},
{"name":"component/language", "color":"bfd4f2"},
{ "name":"component/logging", "color":"bfd4f2"},
{ "name":"component/redis", "color":"bfd4f2"},
{  "name":"component/robot", "color":"bfd4f2"},

0bserver07

Neural Turing Machines: (arXiv:1410.5401)

"We extend the capabilities of neural networks by coupling them to external memory re- sources, which they can interact with by attentional processes."..."Preliminary results demon- strate that Neural Turing Machines can infer simple algorithms such as copying, sorting, and associative recall from input and output examples."

Differentiable Neural Computer: DeepMind /on Nature

"Here we introduce a machine learning model called a differentiable neural computer (DNC), which consists of a neural network that can read from and write to an external memory matrix, analogous to the random-access memory in a conventional computer."..."Taken together, our results demonstrate that DNCs have the capacity to solve complex, structured tasks that are inaccessible to neural networks without external read–write memory."

Scaling Memory-Augmented Neural Networks with Spars