goodpupil

1DCNN

Explanation of 1D CNN

1DCNN-1

1DCNN

1DCNN-2

一维卷积神经网络

1dcnn-3

1DCNN-4

1dcnn-5

1DCNN_Classifier

采用试井压力导数曲线作为训练数据进行油藏模型分类，通过keras构造分类模型

CNN_GRU-Regression

This project use CNN+GRU in tensorflow1.x/python to implement regression about time_series.The main content is to predict the wind power at the current time based on the wind speed and wind power data at the historical time。

Credit-Default-via-Deep-Learning

Using DNN/LSTM/1D-CNN to analyze a credit default problem

SubstancePredication

# Packages installed 1. Anaconda (conda environment with python 3.6) 2. Keras (conda install -c -conda-forge keras) 3. SciKit-learn 4. Pandas 5. Matpotlib 6. NumPy 7. NLTK 8. Wordcloud # Approach I tried to implement 2 approaches, namely a linear neural network model (Sequential) (model 1) and Convolutional Neural Networks (CNN) (model 2), both using Keras libraries. I have commented the code wherever needed and explained the different strategies I tried during the course of this exercise. I prepared 3 datasets: 1. Just the sentence and label columns 2. Subject + Predicate + Object and label columns 3. Both of the above combined. I ran all three datasets and #3 performed better as compared to the other 2. There were key differences in data preparation for both models. In the case of the neural network, I tokenized and vectorized tokens using word2vec from Google News dataset(1x300 array per word) which has information regarding words being contextually relevant. Further, they were weighted by 'term frequency - inverse document frequency'(tf-idf), added together and divided by the count of words. Hence the 'mean' (so-to-speak) of all words of a sentence was calculated forming the word vector of that sentence. Extending this to all rows, the input was of the order: (number of input rows x vector dimensionality of word2vec) In terms of CNN, the input was also tokenized using the Keras library 'Tokenizer' this time and fit the sentences (row) iteratively. Instead of passing the 'mean' of the word vectors, I passed the vectors of a given sentence. I then zero-padded the vectors of sentences until the length was equal to that of the longest amongst the sentences in the input set. Hence the input was of the order: (number of input rows x vector size of the longest sentence) The embedding matrix was the word2vec mapping of all tokens in the input corpus and hence the order of this matrix was: (number of unique tokens x vector dimensionality of word2vec) In both cases, the train-test data split was 80%-20% respectively. # Results I plotted the history of accuracy and losses of the model predictions. Both models yielded around 60% (+/- 3%) accuracy with training and testing. There seems to be no overfitting/underfitting. Metrics for testing sets were as follows: ### Model 1 (Sequential) 1. Accuracy: 0.5833 2. Precision: 0.5548 3. Recall: 0.8571 4. F-score: 0.6736 ### Model 2 (CNN) 1. Accuracy: 0.6233 2. Precision: 0.6056 3. Recall: 0.7143 4. F-score: 0.6555 These results are not terrible but there's room for improvement with hyperparameter tuning and design tweaks for improved metrics. Also, increasing the data volume may result in better metrics. Transfer learning may also be a good option for data this small. # Limitations The metrics showing the model performance could be improved by using more data and tuning hyperparameters. One strategy I skipped is k-fold cross-validation. Implementing k-fold cross-validation may have high variability according to one study and alternatively, they suggest using a new technique called J-K-fold cross-validations to reduce variance during training (https://www.aclweb.org/anthology/C18-1252.pdf). Another strategy I skipped was performing a grid search to arrive at optimized hyperparameter values something that was done by Yoon Kim et.al.. Training deep learning classifiers with a small dataset may not be reliable. Transfer learning may be a better option. Other libraries like fastai (https://docs.fast.ai/) which is a wrapper over PyTorch could be an alternative. They implement sophisticated techniques like 'LR Finder' that helps users make informed decisions on choosing learning rates for optimizers (SGD, Adam or RAdam). They also implement transfer learning wherein an already trained classifier model (on a variety of corpora) is implemented which proves to be effective. They implement advanced Recurrent Neural Network (RNN) strategies. This could be explored in future work.

goodpupil/1dcnn-5

goodpupil/1DCNN_NLP_ASS1

Implementation of One Dimension Convolution Neural Network for Prediction of Housing Data

goodpupil/1dCnn_Non_linear_regression

goodpupil/CIFAR-ZOO

PyTorch implementation of CNNs for CIFAR benchmark

goodpupil/cnn-text-classification-tf

Convolutional Neural Network for Text Classification in Tensorflow

goodpupil/CNN_ATTENTION_models

CNN with attention and CNN_LSTM_attention(pytorch)

goodpupil/CNN_TimeSeriesClassification

goodpupil/CNN_TS

Time series with convolutional neural network

goodpupil/CWT_CNN

Classification of multiple non-stationary time-series by using Continuous Wavelet Transformation

goodpupil/Data_Augmentation-3

Data Augmentation to increase base data size

goodpupil/DeepEEGDataAugmentation

Code for processing EEG data with Riemannian and deep learning-based classifiers. Additionally provides methods for data augmentation including intentionally imbalancing a dataset, and appending modified data to the training set.

goodpupil/End-to-end-Sequence-Labeling-via-Bi-directional-LSTM-CNNs-CRF-Tutorial

Tutorial for End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF

goodpupil/GAN_Time_Series

A model to generate time series data with the purpose of augmenting a dataset of various time series.

goodpupil/General-Purpose-GenP-Bioimage-Ensemble-of-Handcrafted-and-Learned-Features-with-Data-Augmentation

General Purpose (GenP) Bioimage Ensemble of Handcrafted and Learned Features with Data Augmentation

goodpupil/K-fold-CNN-using-Keras

K-fold-CNN for forecasting buyer transaction

goodpupil/keras-data-augmentation-res

goodpupil/LSTM-Neural-Network-for-Time-Series-Prediction

LSTM built using Keras Python package to predict time series steps and sequences. Includes sin wave and stock market data

goodpupil/NLP-1DCNN

assignment 1

goodpupil/Nlp_Assignment1_nonlinear_1dCNN

goodpupil/pos_tagging

Implementation of POS (part-of-speech) tagger with CNN and LSTM using PyTorch

goodpupil/pwc

Papers with code. Sorted by stars. Updated weekly.

goodpupil/PyTorchDocs

PyTorch 官方中文教程包含 60 分钟快速入门教程，强化教程，计算机视觉，自然语言处理，生成对抗网络，强化学习。欢迎 Star，Fork！

goodpupil/Time-Series-Forecasting-using-NN-LSTM-and-CNN

Predicted a stock price close of a day based on the last 7 day’s time series data using Neural Network, LSTM and CNN. Found the best number of the days should be considered in the past that yield the best model. Also, used LSTM to predict the stock prices for a company like Google and Apple for a continuous 5 days period.

goodpupil/time_series_classification_and_ensembles

some examples for time series classification using keras: #1D_CNN #LSTM #Dense #Ensembles

goodpupil/Time_Series_Prediction_TF

Stock prediction using TensorFlow; utilizing methods of LSTM, DNN and CNN.

goodpupil/TimeSeries-CNN

In this project I developed Convolutional Neural Network models for univariate , multivariate , multi-step time series forecasting.

goodpupil/towerDataAugment

我的数据增强备份

goodpupil/video_analysis

ML Pytorch - Model for video analysis and video classification based on encoder(CNN)-decoder(LSTM) architecture.

goodpupil/Visual-Question-Answering

CNN+LSTM, Attention based, and MUTAN-based models for Visual Question Answering

goodpupil/wide-resnet.pytorch

Best CIFAR-10, CIFAR-100 results with wide-residual networks using PyTorch