Keras
Keras adalah API neural network tingkat tinggi, ditulis dengan Python dan mampu berjalan di atas TensorFlow, CNTK, atau Theano. Keras dikembangkan dengan fokus pada memungkinkan eksperimen cepat. Mampu beralih dari ide ke hasil dalam waktu singkat sehingga memungkinkan untuk menjadi kunci untuk melakukan penelitian yang baik.
Gunakan Keras jika anda membutuhkan Library Deep Learning untuk:
- Memungkinkan pembuatan prototipe yang mudah dan cepat (melalui keramahan pengguna, modularitas, dan ekstensibilitas).
- Mendukung convolutional network dan recurrent network, serta kombinasi keduanya.
- Berjalan mulus di CPU dan GPU.
Dokumentasi Keras ada di Keras.io. Keras kompatible dengan: Python 2.7-3.6.
Referensi
- https://keras.io/
- https://github.com/keras-team/keras
- https://github.com/keras-team/keras/tree/master/examples
Pranala Menarik
- Keras: asal usul Keras
- Keras: Konsep Secara Umum
- Regresi Linier
- Keras: Instalasi
- Keras: Konfigurasi Backend
- Keras: LSTM IoT
First Time
- Keras: Develop Your First Neural Network in Python Step-By-Step
- Keras: Memilih Fungsi Loss
- Keras: Loss and Loss Function
- Keras: Introduction to the Adam Optimization Algorithm
- Keras: Difference Between a Batch and an Epoch
- Keras: Embrace Randomness
- Keras: Evaluate the Skill of Deep Learning Model
- Keras: Save and Load Your Keras Deep Learning Model
- Keras: Gradient Descent For Machine Learning
- Keras: Introduction to Mini-Batch Gradient Descent
- Keras: Introduction to Learning Curves for Diagnosing Model Performance
Vision models examples
- Trains a simple deep multi-layer perceptron on the MNIST dataset
- Trains a simple convnet on the MNIST dataset
- Keras Image Classification
- Trains a simple deep CNN on the CIFAR10 small images dataset
- Trains a simple CNN-Capsule Network on the CIFAR10 small images dataset
- Trains a ResNet on the CIFAR10 small images dataset
Time Series
- https://machinelearningmastery.com/time-series-prediction-lstm-recurrent-neural-networks-python-keras/
- https://towardsdatascience.com/using-lstms-for-stock-market-predictions-tensorflow-9e83999d4653
- https://www.kdnuggets.com/2018/11/keras-long-short-term-memory-lstm-model-predict-stock-prices.html
Dasar
- Keras: read csv timeseries
- TimeSeries: Anomaly detection in a time series
- TimeSeries: Using Tensorflow for time series modelling and forecasting
- TimeSeries: LSTM untuk IoT
Text
Sentimen Analysis
- https://github.com/shaypal5/awesome-twitter-data # Twitter Data Set
- https://www.kaggle.com/ngyptr/lstm-sentiment-analysis-keras
- https://www.kaggle.com/drscarlat/imdb-sentiment-analysis-keras-and-tensorflow
- https://towardsdatascience.com/machine-learning-word-embedding-sentiment-classification-using-keras-b83c28087456
- https://github.com/keras-team/keras/blob/master/examples/imdb_lstm.py
- https://github.com/keras-team/keras/blob/master/examples/imdb_cnn_lstm.py
- https://github.com/keras-team/keras/blob/master/examples/imdb_bidirectional_lstm.py
- Keras - LSTM Sentiment Positif and Negatif Analysis
- Keras - IMDB Sentiment-Analysis Keras and TensorFlow
Speech / Audio
Prediction
- Keras: LabelEncoder
- Keras: Cara Training Final Machine Learning Model
- Keras: Prediction
- Keras: 5 Step Life-Cycle for Long Short-Term Memory Model
- Keras: Make Predictions with Long Short-Term Memory Model
Unsupervised Learning