2020

06-22 Attention is all you need
06-10 Transformer Primer : Jay Allamar
06-10 BERT Neural Network Explained, Transformers
06-10 Attention Primer : Jay Allamar
03-18 Information Theory Book Review
03-15 Machine Learning for Business Using Amazon SageMaker and Jupyter
02-08 A Big Data Hadoop and Spark project for absolute beginners

2019

11-26 O’Reilly Datashow: Apache Spark Journey from Academia to Industry
11-25 Data Science makes an impact on Wall Street
11-24 Maching Learning for Indexing
11-02 Ian GoodFellow Interview
11-01 Bert Limitations
10-19 Indistractable - Book Summary
10-12 My Learnings from attending PyCon SG19 Tutorial on Deep Learning
10-12 Multiprocessing vs. Threading in Python: What Every Data Scientist Needs to Know
09-26 Data Leakage
09-25 MASE
09-25 Forecasting time series using R by Prof Rob J Hyndman
09-18 Using Transfer Learning and Pre-trained Language Models to Classify Spam
09-18 Embeddings in NLP and beyond
09-18 BERT
09-13 LSTM Models for Simulated Time Series data
09-13 Heuristics
09-12 Early Stopping in Keras
09-11 Generative LSTM
09-10 Stacked LSTM
09-10 Sequence to Sequence LSTM
09-10 Plain Vanilla LSTM
09-10 LSTM output
09-10 Bidirectional LSTM
09-08 Ultra Learning - Book Review
09-07 Spacy Deliberate Practice
09-07 NLP - Natural Language Processing with Python - Jose Portilla
09-06 Sentiment Analysis via LSTM
09-06 Generating text via SimpleRNN
09-03 Train an XOR using Simple RNN
09-03 Train a Simple RNN to track cumulative sums
09-03 Train a Simple RNN to track a simple shift
09-03 Train a Simple RNN to track a shift sampled from a normal distribution
08-26 Example of why word embeddings matter
08-23 The Transformer
08-14 The Transformer
08-14 Mapping Dialects with Twitter Data
08-07 The Death of a Language
08-07 Named Entity Recognition
08-06 Simultaneous Translation
08-06 Sequence to Sequence Models
08-02 Human vs Machine Transcription
07-31 Data Skeptic - Word Embeddings Lower Bound

2018

07-01 Index Funds and ETFs