Welcome to the AIBridge Course homepage.

The purpose of AIBridge is to bridge the gap between computer science and other disciplines. To many, working with AI might seem like an unreachable objective. However, in reality, one week is enough to get started. AIBridge will provide basic programming capability in Python and knowledge of object-oriented programming as well as the concepts behind machine learning and how to implement it using a popular toolbox, Scikit-Learn. Students work to complete a personally-defined project using techniques in AI, with data from their own research or with problems supplied by the Course. This one week course will be hosted in-person at UC Davis and will target mainly undergraduate and non-technical graduate students.

Part 1: ML Training Practice

One of the things that makes a very good Sommelier is their ability to figure out as much details about a wine as possible with very little information.

You are tasked with making a Sommelier program that is able to figure both the type and quality of wine from available chemical information. Also, you have a “flavor-ater” machine that makes a linear combination of multiple chemical features together (similar to PCA), which is counted as one chemical feature after combination.

SPOILER ALERT for future labs!! Don’t scroll down!

We are going to create a copy of the iris dataset with a random variance.

import sklearn
from sklearn.datasets import load_iris

Let’s load the iris dataset:

x,y = load_iris(return_X_y=True)

Because we need to generate a lot of random data, let’s import random

import random

Put this in a df

import pandas as pd
df = pd.DataFrame(x)
df

       0    1    2    3
0    5.1  3.5  1.4  0.2
1    4.9  3.0  1.4  0.2
2    4.7  3.2  1.3  0.2
3    4.6  3.1  1.5  0.2
4    5.0  3.6  1.4  0.2
..   ...  ...  ...  ...
145  6.7  3.0  5.2  2.3
146  6.3  2.5  5.0  1.9
147  6.5  3.0  5.2  2.0
148  6.2  3.4  5.4  2.3
149  5.9  3.0  5.1  1.8

[150 rows x 4 columns]

Let’s make 150 random numbers with pretty low variance:

This is usually not needed if you are using Google Colab. If you are following the instructions provided during our lecture series, please disregard this page.

However, students have expressed interest in working with their own system’s copy of Jupyter or local installation. We therefore provide a set of very tenuous instructions for installing the tools used in our session using vanilla C-Python (i.e. not anaconda/conda/miniconda.)

Python

Our tools target Python 3.8+. Use your system’s package manager to install Python at least version 3.8, or use Python Foundation’s universal installers.

Rewa Rai

Nitin Lab, Dept. of Food Sci + Tech - Davis

Wine

Classification Task

Whole data:

• Decision Tree: 98.46%
• Random Forest: 99.84%
• Gaussian NB: 97.08%

Regression Task

Feature selection with 2 best features actually improved.

Talkthrough

Detecting berry infection by leaf classification. Use FTIR spectroscopy as a means of infection classification.

Tana Hernandez

PHD Student, Nitin Lab, Dept. of Food Sci + Tech - Davis

Talkthrough

Given input for reaction, predict resulting gell strength from protein+carbo+lactic acid.