For a particular layer, different implementations are possible

For the layer above, all different implementations [...]

For a particular layer, different implementations are possible

For the layer [...], all different implementations (ideally) look the same

Initialize array with constants

[...]

Pointer type void

void* a; // pointer variable with unspecified target type

• Assignment from [...] to void* valid
• No address arithmetic on void* because size of elements unknown
• Cast to non-void pointer required before usage:

double* d[10];

a = &d;
/*
↓ Derefence double* */
* (double*) a = 3.2;
/*    ↑ Cast a to double*  */

Pointer type void

void* a; // pointer variable with unspecified target type

• Assignment from any pointer type to void* valid
• [...] address arithmetic on void* because size of elements unknown
• Cast to non-void pointer required before usage:

double* d[10];

a = &d;
/*
↓ Derefence double* */
* (double*) a = 3.2;
/*    ↑ Cast a to double*  */

Pointer type void

• [...] required before usage:

Cast to non-void pointer

Example:

double* d[10];

a = &d;
/*
↓ Derefence double* */
* (double*) a = 3.2;
/*    ↑ Cast a to double*  */

void* malloc(size_t size); // declared in stdlib.h

• Allocates memory block of size bytes
• Returns [...]
• Content of memory block undefined

void* malloc(size_t size); // declared in stdlib.h

• Allocates memory block of size bytes
• Returns pointer to start of memory block
• Content of memory block [...]

void* malloc(size_t size); // declared in stdlib.h

• Allocates [...] of size bytes
• Returns pointer to start of memory block
• Content of memory block undefined

[...] operator `->`

struct point* b =malloc(sizeof(struct point));
b->x;

Member-access-through-pointer operator [...]

struct point* b =malloc(sizeof(struct point));
b->x;

[...] & yields address of a variable

int i= 42;
printf("%p", &i); // print address of i

Address-of operator [...] yields address of a variable

int i= 42;
printf("%p", &i); // print address of i

Address-of operator & [...]

int i= 42;
printf("%p", &i); // print address of i

[...] macro definition

➜ Preprocessor replaces all occurrences of macro by definition

#define macro definition

➜ [...] replaces all occurrences of macro by definition

#define macro definition

➜ Preprocessor [...]

How we can improve model (in the particular stage of the process)?

# 1. Creating model: add [...], increase numbers of hidden neurons, change activation functions

Confusion matrix

[...]-axis -> true label

## The 3 sets (or actually 2 sets: training and test set) - USING ONLY TensorFlow

tf.random.set_seed(999)

X_train, X_test = tf.split(tf.random.[...](X, seed=42), num_or_size_splits=[40, 10])

What can visualize?

• the data
• [...] itself
• the training of a model
• predictions

How we can improve model (in the particular stage of the process)?

# 2. Compiling: change [...] or its parameters (eg. learning rate)

Step 1 is to gather the data. You'll notice that there's a bit of a change here in that the training data needed to be reshaped. That's because the first convolution expects a single tensor containing everything, so instead of 60,000 28x28x1 items in a list, we have a single 4D list that is 60,000x28x28x1, and the same for the test images. If you don't do this, you'll get an error when training as the Convolutions do not recognize the shape.

import tensorflow as tf
mnist = tf.keras.datasets.fashion_mnist
(training_images, training_labels), (test_images, test_labels) = mnist.load_data()
training_images=training_images.reshape(60000, 28, 28, 1)
training_images=training_images / 255.0

model = tf.keras.models.Sequential([
  tf.keras.layers.Conv2D(64, (3,3), activation='relu', [...]=(28, 28, 1)),
  tf.keras.layers.MaxPooling2D(2, 2),
  tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
  tf.keras.layers.MaxPooling2D(2, 2),
  tf.keras.layers.Flatten(),
  tf.keras.layers.Dense(128, activation='relu'),
  tf.keras.layers.Dense(10, activation='softmax')
])