2023年11月25日

Python代写 | IN3062: Introduction to Artificial Intelligence

本次Python代写是将人工智能技术应用于选择的数据集和域

IN3062: Introduction to Artificial Intelligence
Coursework

The Task
In this coursework, you are expected to demonstrate what you have learned in the module by
applying artificial intelligence techniques as covered in the module to a dataset and domain
of your choice. This will include some or all of:
• Define the domain and dataset(s) (you are free to choose the domain and the dataset that
you want to investigate).
• Define questions and analysis tasks (a brief overview of the domain, analytical
questions that are being asked, a list of your objectives and the expected output(s) of your
analysis).
• Perform an initial investigation of the dataset and the characteristics of the data. Develop
a viable plan: which data processing steps you will need to perform, how you will
transform the data to make it useable, which artificial intelligence techniques you can
potentially use and what sorts of potential observations these can lead to.
• Perform the analysis. Get the data ready for analysis, carry out your analysis/modelling
as needed, validate your results and communicate observations, iterating through this
process. Analytical operations can include data processing to an extent that is needed
(not all datasets are messy) to prepare a useful and robust dataset to work within, and data
derivation (such as feature engineering).
• Split your dataset (train/validate/test, some datasets come pre-split). If you have a holdout
test set then you most likely don’t want to use this until the near the end of your work.
• You might establish a baseline result first, computing metrics on training and validation
sets, analyse errors, work on succeeding iterations, and alternative models. (If initial
metrics are amazing and there are no errors is the problem too easy?)
• Be close to your data (visualise the dataset, collect summary statistics, look at errors,
analyse how different parameters affect performance, try out different model variants).