Delve into practical machine learning with NumPy, pandas, scikit-learn, and more. Gain insights into data analysis, feature engineering, and deep learning using industry-standard frameworks. Basic Python required.

ml.tar.gz

mnist-fashion

If you're a software engineer looking to add machine learning to your skillset, this is the place to start. 

This course will teach you to write useful code and create impactful machine learning applications immediately. From the start, you'll be given all the tools that you need to create industry-level machine learning projects. Rather than reading through dense theory, you’ll learn practical skills and gain actionable insights. Topics covered include data analysis/visualization, feature engineering, supervised learning, unsupervised learning, and deep learning. All of these topics are taught using industry-standard frameworks: NumPy, pandas, scikit-learn, XGBoost, TensorFlow, and Keras.

Basic knowledge of Python is a prerequisite to this course.

This course was created by AdaptiLab, a company specializing in evaluating, sourcing, and upskilling enterprise machine learning talent. It is built in collaboration with industry machine learning experts from Google, Microsoft, Amazon, and Apple.

Machine Learning with NumPy, pandas, scikit-learn, and More

## Chapter Goals:
<ul>
 <li>Build a single fully-connected model layer</li>
 <li>Output logits, AKA log-odds</li>
</ul>

<h2>A. Fully-connected layer</h2>
Before we can get into multilayer perceptrons, we need to start off with a single layer perceptron. The single fully-connected layer means that the input layer, i.e. <code>self.inputs</code>, is directly connected to the output layer, which has <code>output_size</code> neurons. Each of the <code>input_size</code> neurons in the input layer has a connection to each neuron in the output layer, hence the fully-connected layer.

In TensorFlow, this type of fully-connected neuron layer is implemented using <code><a href="https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dense" target="_blank">tf.keras.layers.Dense</a></code>, which takes in a neuron layer and output size as required arguments, and adds a fully-connected output layer with the given size to the computation graph.
In addition to the input layer neurons, <code>tf.keras.layers.Dense</code> adds another neuron called the bias, which always has a value of 1 and has full connections to the output layer.

The bias neuron helps our neural network produce better results, by allowing each fully-connected layer to model a true linear combination of the input values.

<h2>B. Weighted connections</h2>
The forces that drive a neural network are the real number weights attached to each connection. The weight on a connection from neuron A into neuron B tells how strongly A affects B as well as whether that effect is positive or negative, i.e. direct vs. inverse relationship.

The diagram above has three weighted connections:
A &rarr; B: Direct relationship. 
A &rarr; C: No relationship. A &rarr; D: Inverse relationship.
The weighted connections allow fully-connected layers to model a linear combination of the inputs. Let's take a look at an example fully-connected layer with weights:

# Chapter Goals:
<ul>
 <li>Build a single fully-connected model layer</li>
 <li>Output logits, AKA log-odds</li>
</ul>

Dive into the inner layers of a neural network and understand the importance of logits.

What you'll learn from this course

Data Manipulation with NumPy

Data Analysis with pandas

Data Preprocessing with scikit-learn

Data Modeling with scikit-learn

Clustering with scikit-learn

Gradient Boosting with XGBoost

Deep Learning with TensorFlow

Deep Learning with Keras

Logits

Chapter Goals:

A. Fully-connected layer

B. Weighted connections