shagunsodhani

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

nzw0301

*2vec papers

1. act2vec, trace2vec, log2vec, model2vec https://link.springer.com/chapter/10.1007/978-3-319-98648-7_18
2. apk2vec https://arxiv.org/abs/1809.05693
3. app2vec http://paul.rutgers.edu/~qma/research/ma_app2vec.pdf
4. ast2vec https://arxiv.org/abs/2103.11614
5. attribute2vec https://arxiv.org/abs/2004.01375
6. author2vec http://dl.acm.org/citation.cfm?id=2889382
7. baller2vec https://arxiv.org/abs/2102.03291
8. bb2vec https://arxiv.org/abs/1809.09621

karpathy

""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
import numpy as np
import cPickle as pickle
import gym

# hyperparameters
H = 200 # number of hidden layer neurons
batch_size = 10 # every how many episodes to do a param update?
learning_rate = 1e-4
gamma = 0.99 # discount factor for reward

fchollet

'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.
It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data
In our setup, we:
- created a data/ folder
- created train/ and validation/ subfolders inside data/
- created cats/ and dogs/ subfolders inside train/ and validation/
- put the cat pictures index 0-999 in data/train/cats

anj1

import types
import tensorflow as tf 
import numpy as np

# Expressions are represented as lists of lists,
# in lisp style -- the symbol name is the head (first element)
# of the list, and the arguments follow.

# add an expression to an expression list, recursively if necessary.
def add_expr_to_list(exprlist, expr):

shagunsodhani

Key-Value Memory Networks for Directly Reading Documents

Introduction

• Knowledge Bases (KBs) are effective tools for Question Answering (QA) but are often too restrictive (due to fixed schema) and too sparse (due to limitations of Information Extraction (IE) systems).
• The paper proposes Key-Value Memory Networks, a neural network architecture based on Memory Networks that can leverage both KBs and raw data for QA.
• The paper also introduces MOVIEQA, a new QA dataset that can be answered by a perfect KB, by Wikipedia pages and by an imperfect KB obtained using IE techniques thereby allowing a comparison between systems using any of the three sources.
• Link to the paper.

Related Work

udibr

import numpy as np
from keras.layers import GRU, initializations, K
from collections import OrderedDict

class GRULN(GRU):
    '''Gated Recurrent Unit with Layer Normalization
    Current impelemtation only works with consume_less = 'gpu' which is already
    set.

    # Arguments

dirko

# Keras==1.0.6
import numpy as np
from keras.models import Sequential
from keras.layers.recurrent import LSTM
from keras.layers.core import TimeDistributedDense, Activation
from keras.preprocessing.sequence import pad_sequences
from keras.layers.embeddings import Embedding
from sklearn.cross_validation import train_test_split
from sklearn.metrics import confusion_matrix, accuracy_score, precision_recall_fscore_support

hal3

"""
PyTorch implementation of a sequence labeler (POS taggger).

Basic architecture:
 - take words
 - run though bidirectional GRU
 - predict labels one word at a time (left to right), using a recurrent neural network "decoder"

The decoder updates hidden state based on:
 - most recent word

kumarbhrgv

Improvising diversity of personalized recommendation systems

Recent Research papers:

• Improving Aggregate Recommendation Diversity Using Ranking-Based Techniques:

  107 Citations : IEEE Transactions on Knowledge and Data Engineering
  we introduce and explore a number of item ranking techniques that can generate substantially more diverse recommendations across all users while maintaining comparable levels of recommendation accuracy. Comprehensive empirical evaluation consistently shows the diversity gains of the proposed techniques using several real-world rating data sets and different rating prediction algorithms

• Recommendation Diversification Using Explanations: (Data Engineering, 2009. ICDE '09. IEEE 25th International Conference)

Traditionally, the problem is addressed through attribute-based diversification grouping items in the result set that share many common attributes (e.g., genre for movies) and selecting only a limited number of items from each group. It is, however,