bbrighttaer

18:17:08.937 [application-akka.actor.default-dispatcher-4] ERROR application - 

! @766o9k5ib - Internal server error, for (GET) [/train/model/graph] ->
 
play.api.http.HttpErrorHandlerExceptions$$anon$1: Execution exception[[InvocationTargetException: null]]
	at play.api.http.HttpErrorHandlerExceptions$.throwableToUsefulException(HttpErrorHandler.scala:265)
	at play.api.http.DefaultHttpErrorHandler.onServerError(HttpErrorHandler.scala:191)
	at play.core.server.netty.PlayDefaultUpstreamHandler$$anonfun$9$$anonfun$apply$1.applyOrElse(PlayDefaultUpstreamHandler.scala:151)
	at play.core.server.netty.PlayDefaultUpstreamHandler$$anonfun$9$$anonfun$apply$1.applyOrElse(PlayDefaultUpstreamHandler.scala:148)
	at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:33)

bbrighttaer

Curriculum Learning

Introduction

• Curriculum Learning - When training machine learning models, start with easier subtasks and gradually increase the difficulty level of the tasks.
• Motivation comes from the observation that humans and animals seem to learn better when trained with a curriculum like a strategy.
• Link to the paper.

Contributions of the paper

bbrighttaer

# project: fuzzrl
# Copyright (C) 6/8/18 - 2:54 PM
# Author: bbrighttaer


"""
slight modification of scikit-fuzzy skfuzzext.py : RuleOrderGenerator
"""

from skfuzzy.control.controlsystem import RuleOrderGenerator

bbrighttaer

/home/bbrighttaer/anaconda3/envs/deepchem/lib/python3.5/site-packages/deepchem/feat/rdkit_grid_featurizer.py:1033: UserWarning: sanitize is set to False, pi_stack feature will be ignored
  feature_type)
/home/bbrighttaer/anaconda3/envs/deepchem/lib/python3.5/site-packages/deepchem/feat/rdkit_grid_featurizer.py:1033: UserWarning: sanitize is set to False, cation_pi feature will be ignored
  feature_type)
Featurizing Complexes
TIMING: Loading protein coordinates took 68.712 s
TIMING: Loading ligand coordinates took 0.226 s
TIMING: Centroid processing took 0.031 s
TIMING: Loading protein coordinates took 56.752 s
TIMING: Loading ligand coordinates took 0.258 s

bbrighttaer

# Author: bbrighttaer
# Date: 5/24/19
# Time: 12:27 AM
# File: math.py


from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals

bbrighttaer

from __future__ import absolute_import, division, print_function, unicode_literals

import numpy as np
import rdkit.Chem as Chem
from rdkit import DataStructs
from rdkit.Chem import AllChem


def verify_sequence(smile):
    mol = Chem.MolFromSmiles(smile)

bbrighttaer

def default_hparams_bopt(flags):
    """
    protein model types:
    --------------------------------------------------------------------------------------------
    short name  | full name
    ------------|-------------------------------------------------------------------------------
    psc         | Protein Sequence Composition
    ------------|-------------------------------------------------------------------------------
    p2v         | Protein to Vector / Embeddings using n-gram amino acid 'words'.
    ------------|-------------------------------------------------------------------------------

bbrighttaer

(base) MacBook-Pro build % cmake ..
-- Found ZLIB: /opt/local/lib/libz.dylib (found version "1.2.12") 
-- Configuring done
-- Generating done
-- Build files have been written to: /Users/bbrighttaer/robocup-soccer/rcssmonitor-17.0.0/build
(base) MacBook-Pro build % make
[  2%] Automatic MOC for target rcssrcg
[  2%] Built target rcssrcg_autogen
[  5%] Building CXX object rcss/rcg/CMakeFiles/rcssrcg.dir/rcssrcg_autogen/mocs_compilation.cpp.o
[  7%] Building CXX object rcss/rcg/CMakeFiles/rcssrcg.dir/handler.cpp.o

bbrighttaer

Source: https://github.com/philparadis/paper-notes/issues/1

Step 1:
Read the article diagonally, highlighting all key terminology, concepts, algorithms, etc. I need to be familiar with
Make a first quick summary of what I think the paper is trying to establish

Step 2:
Find the definitions of the previously highlighted key prerequisites (concepts, algorithms, terminology)
Find the most important articles listed in the reference section and go through them