Introduction to TensorFlow W1:A New Programming Paradigm

by Laurence Moroney

Code

import tensorflow as tf
import numpy as np
from tensorflow import keras

print(tf.__version__)

2.16.1

Code

# Build a simple Sequential model
model = tf.keras.Sequential([keras.layers.Dense(units=1, input_shape=[1])])

Code

# Compile the model
model.compile(optimizer='sgd', loss='mean_squared_error')

Code

# Declare model inputs and outputs for training
xs = np.array([-1.0,  0.0, 1.0, 2.0, 3.0, 4.0], dtype=float)
ys = np.array([-3.0, -1.0, 1.0, 3.0, 5.0, 7.0], dtype=float)

Code

# Train the model
model.fit(xs, ys, epochs=500,verbose=0)

<keras.src.callbacks.history.History at 0x2848f63d0>

Code

# Make a prediction
print(model.predict(x=np.array([10.0])))

1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 13ms/step1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 13ms/step
[[18.976614]]

1 resource:

https://www.coursera.org/learn/introduction-tensorflow/home/info

https://github.com/https-deeplearning-ai/tensorflow-1-public/tree/main/C1

---
title: "W1:A New Programming Paradigm"
execute:
  warning: false
  error: false
format:
  html:
    toc: true
    toc-location: right
    code-fold: show
    code-tools: true
    number-sections: true
    code-block-bg: true
    code-block-border-left: "#31BAE9"
---


Week1 A New Programming Paradigm

Welcome to this course on going from Basics to Mastery of TensorFlow. We're excited you're here! In week 1 you'll get a soft introduction to what Machine Learning and Deep Learning are, and how they offer you a new programming paradigm, giving you a new set of tools to open previously unexplored scenarios. All you need to know is some very basic programming skills, and you'll pick the rest up as you go along.

You'll be working with code that works well across both TensorFlow 1.x and the TensorFlow 2.0 alpha. To get started, check out the first video, a conversation between Andrew and Laurence that sets the theme for what you'll study...



by Laurence Moroney

![](images/2-01.png){width="365"}

```{python}
import tensorflow as tf
import numpy as np
from tensorflow import keras

print(tf.__version__)
```

```{python}
# Build a simple Sequential model
model = tf.keras.Sequential([keras.layers.Dense(units=1, input_shape=[1])])
```

```{python}
# Compile the model
model.compile(optimizer='sgd', loss='mean_squared_error')
```

```{python}
# Declare model inputs and outputs for training
xs = np.array([-1.0,  0.0, 1.0, 2.0, 3.0, 4.0], dtype=float)
ys = np.array([-3.0, -1.0, 1.0, 3.0, 5.0, 7.0], dtype=float)
```

```{python}
# Train the model
model.fit(xs, ys, epochs=500,verbose=0)
```

```{python}
# Make a prediction
print(model.predict(x=np.array([10.0])))
```

# resource:

https://www.coursera.org/learn/introduction-tensorflow/home/info

https://github.com/https-deeplearning-ai/tensorflow-1-public/tree/main/C1