Introduction to deep learning

Nhập môn Deep Learning với Python

Dan Becker

Data Scientist and contributor to Keras and TensorFlow libraries

Imagine you work for a bank

You need to predict how many transactions each customer will make next year

Example as seen by linear regression

ch1_1.003.png

Example as seen by linear regression

ch1_1.004.png

Example as seen by linear regression

ch1_1.005.png

Example as seen by linear regression

ch1_1.006.png

Example as seen by linear regression

ch1_1.007.png

Example as seen by linear regression

ch1_1.008.png

Example as seen by linear regression

ch1_1.009.png

Example as seen by linear regression

ch1_1.011.png

Example as seen by linear regression

ch1_1.012.png

Example as seen by linear regression

ch1_1.013.png

Example as seen by linear regression

ch1_1.014.png

Example as seen by linear regression

ch1_1.015.png

Example as seen by linear regression

ch1_1.016.png

Example as seen by linear regression

ch1_1.017.png

Interactions

Neural networks account for interactions really well
Deep learning uses especially powerful neural networks
- Text
- Images
- Videos
- Audio
- Source code

Course structure

First two chapters focus on conceptual knowledge
- Debug and tune deep learning models on conventional prediction problems
- Lay the foundation for progressing towards modern applications
This will pay off in the third and fourth chapters

Build and tune deep learning models using keras

import numpy as np
from tensorflow.keras.layers import Dense
from tensorflow.keras.models import Sequential
predictors = np.loadtxt('predictors_data.csv', delimiter=',')
n_cols = predictors.shape[1]
model = Sequential()

model.add(Dense(100, activation='relu', input_shape = (n_cols,)))
model.add(Dense(100, activation='relu'))
model.add(Dense(1))