Loading
Feedback

alarih 0

Badges

0
0
0

Activity

Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mon
Wed
Fri

Ratings Progression

Loading...

Challenge Categories

Loading...

Challenges Entered

Multi-Agent Reinforcement Learning on Trains

Latest submissions

See All
failed 71604
graded 70352

Play in a realistic insurance market, compete for profit!

Latest submissions

See All
graded 118159
graded 116163
graded 116158

Predicting smell of molecular compounds

Latest submissions

See All
graded 120340
graded 120339
failed 120318

Latest submissions

See All
graded 121542
graded 119205
graded 119101

Multi Agent Reinforcement Learning on Trains.

Latest submissions

See All
graded 24663
graded 24662
failed 24499

Predict Labor Class

Latest submissions

See All
graded 72697
graded 72685
failed 72681

Predict Win Depth

Latest submissions

See All
graded 72717

Detect critical heart failures in infants

Latest submissions

See All
graded 89784

Extrapolate Time Series Data

Latest submissions

See All
graded 119374
graded 115964
graded 115962

Recognise Text From Images

Latest submissions

See All
graded 118482
graded 118464
graded 118445

Color Black and White Images

Latest submissions

See All
graded 118390
graded 118382
graded 115969

Detect Objects From Images

Latest submissions

See All
graded 118808
graded 118807
graded 118726

Analyse Sentiment From Sound Clips

Latest submissions

See All
graded 118863
failed 118862
graded 115758

Predict moves of a chess piece from video snippet

Latest submissions

See All
graded 123828

Predict chessboard configuration from an image

Latest submissions

See All
graded 123956
graded 123942
graded 123932

Predict the side with highest points.

Latest submissions

See All
graded 123686

Identify which side has least players

Latest submissions

See All
graded 123684

Predict the winner through prior chess moves

Latest submissions

See All
graded 123689
Gold 0
Silver 0
Bronze 0

Badges


  • May 16, 2020
Participant Rating
nima 54
Participant Rating
alarih has not joined any teams yet...

Request for a teammate

About 14 hours ago

Hey, thank you. I think I have transcription figured out

Learning to Smell

#3 solution to Learning to Smell

10 days ago

thanks. yeah, that step gave a small boost.
I had 2 ways to get validation scores:

  • out of fold score for individual models: around .39
  • average prediction of fold models on the held out set: around .41
    LB: around .31
    It’s possible that the distribution of the test smells was different from what we had in the train set or molecules were structurally different, hence the discrepancy between LB and validation. In previous rounds results were much closer.

#3 solution to Learning to Smell

11 days ago

This was one of my favorite challenges so far, because the problem formulation is very simple and it attempts to get insight into one of our primal but neglected basic senses. My solution was far behind top 2 competitors, so I feel like I was missing some crucial ingredient, so I am looking forward to learn about their approach.

The core of my approach is neural net on fingerprints.

  1. Data: union of various fingerprints extracted with rdkit from the SMILES in train set

    from rdkit import Chem
    from rdkit.Chem import AllChem
    from rdkit.Chem import MACCSkeys
    mol = Chem.MolFromSmiles(smiles)
    
    fp0 = MACCSkeys.GenMACCSKeys(mol) # MACCS keys
    fp1 = AllChem.GetMorganFingerprintAsBitVect(mol, 2, 256) # Morgan fingerprints
    fp2 = Chem.RDKFingerprint(mol)
    fp3 = [len(mol.GetSubstructMatch(Chem.MolFromSmarts(smarts)) > 0 for smarts in smarts_inteligands] # smarts_inteligands has about 305 smarts patterns
    
    
    
  2. Preprocessing: drop constant and duplicate fingerprints

  3. Model:

    from torch import nn
    hidden_size = 512
    dropout = .3
    output_size = 75
    nn.Sequential(
                nn.Linear(input_size, hidden_size),
                nn.ReLU(inplace=True),
                nn.Dropout(dropout),
                nn.BatchNorm1d(hidden_size),
                nn.Linear(hidden_size, hidden_size),
                nn.ReLU(inplace=True),
                nn.Dropout(dropout),
                nn.BatchNorm1d(hidden_size),
                nn.Linear(hidden_size, output_size),
            )
    
  4. Training was done over 5 folds, each one for 25 epochs with nn.BCEWithLogitsLoss. The model tried to predict probabilities of 75 smells.

  5. The last step was to come up with 5 prediction sequences starting from individual smell probabilities. For this I sampled smells using their predicted probabilities and found the sequence with the best jaccard score. Then found the next sequence with the best incremental jaccard score and so on.

  6. Bells and whistles. Some of the things that made small improvements:

  • label smoothing
  • weighting labels for training
  • weighting fingerprints based on their estimate importance
  1. Things that didn’t work:
  • PCA on features and on labels
  • UMAP on features and on labels
  • pretraining on 109 labels
  • continous version of IOU loss instead of BCE for training
  • various learning rate schedulers
  • dropping fingerprints with high correlation to others
  • trying another dropout/learning rate

TIMSER

#1 Solution to TIMSER Blitz5

21 days ago

Well, when I submitted MSE=3333333.333 solution, I already knew the answer, so just added some noise to make it look cute.
But to your point, I looked at the distribution of fractional values and ran a couple of linear regressions. Fractional values in this data had some distinct pattern. Single stock prices usually get adjusted because of splits and dividends, so the distribution of their fractional values didn’t match the pattern. Indices on the other hand don’t get adjusted, so I searched for the combination of indices.

Overall, I think it was a great puzzle and a lot of fun to solve.

IMGCOL

#1 Solution IMGCOL Blitz5

21 days ago

my guess is because the colorizers library opens image using PIL, so it has different convention on channel ordering than cv2.

alarih has not provided any information yet.

Notebooks

Create Notebook