Program Overview
Nexus AI
The Nexus AI Program is a 16-week initiative mentored by domain specialistsdesigned to equip students with the skills to apply AI toward research and social good projects that serve a meaningful purpose towards the community.
Apply now for FREE!
Apply before 11:59pm on January 24th, 2025. We will be accepting the top 50 applicants.
Learn Machine Learning and Deep Learning Concepts and Apply Them For Social-Good Research Projects & Research
About the program in a nutshell:
Program Syllabus
Pre-Coursework
- Asynchronous
- Python
- Preprocessing Libraries
- PyTorch Basics
- Concepts & Math of ML/DL
- Assignments & Mini-Projects
Phase One
DL Lectures
- Weekly 3-Hour Lectures
- Neural Network Architectures
- Computer Vision, NLP, LLMs
- Mini-Projects & Practice
Phase One
ML Readings
- Weekly Readings
- Scikit-Learn
- Regression
- Classification Algorithms
- Clustering Algorithms
- Mini-Projects
Phase Two
Mentorship
- 8-Week Research Project
- 1-on-1 Weekly Mentorship
- Present @ NARC
Phase One & Two
Workshops
- Founder-Led Workshops
- Research Plan & Ideation
- Technical Guidance
- Paper Writing
- Posters & Presentation
Pre-Coursework Curriculum
Releasing on January 6, 2025!
This content is designed to be completed asynchronously before the start of the Nexus AI program.
Completion of pre-coursework will ensure that students will be well-versed in fundamental skills prior to the instruction in Phase One.
Section 1 | Essentials of Python
- Learn fundamentals of Python!
- Complete problem sets!
- Apply concepts to mini-projects!
Concept 1.1: Variables & Data Types
- Variables
- Strings
- Integers
- Floats
- Booleans
- Problem Set 1.1
Concept 1.2: Simple Data Structures & Print Statements
- Lists
- Dictionaries
- Tuples
- Sets
- Print Statements
- Input & Output (I/O)
- Basic Debugging
- Problem Set 1.2
Mini-Project 1.1: Personal Expense Tracker
- User enters name, category, and amount of expense; expenses & metrics are stored in various data structures.
- Develop mastery of data types
- Improve skills with I/O and print statements
- Efficiently use data structures
Concept 1.3: Operators
- Assignment Operators
- Equals Sign (=)
- Addition Assignment (+=)
- Subtraction Assignment (-=)
- Multiplication Assignment (*=)
- Division Assignment (/=)
- Modulus Assignment (%=)
- Exponent Assignment (**=)
- Floor Division Assignment (//=)
- Problem Set 1.3
- Arithmetic Operators
- Addition (+)
- Subtraction (-)
- Multiplication (*)
- Division (/)
- Modulus (%)
- Exponentiation (**)
- Floor Division (//)
- Problem Set 1.4
- Comparison (Relational) Operators
- Equal (==)
- Not Equal (!=)
- Greater Than (>)
- Less Than (<)
- Greater Than or Equal To (>=)
- Less Than or Equal To (<=)
- Problem Set 1.5
- Logical & Bitwise Operators
- Logical And (and, &&)
- Logical Or (or, | )
- Logical Not (not, !)
- Bitwise And (&)
- Bitwise Or ( | )
- Bitwise Xor (^)
- Bitwise Not (~)
- Left Shift (<<)
- Right Shift (>>)
- Problem Set 1.6
- Identity & Membership Operators
- is / is not
- in / not in
- Problem Set 1.7
Concept 1.4: Conditional Statements
- If-Elif-Else Statements & Syntax
- Problem Set 1.8
Mini-Project 1.2: Grade Calculator
- User enters point value & points earned for 10 assignments; calculator determines student’s letter grade.
- Gain mastery of operators
- Learn when & how to use if-elif-else statements
- Gain experience in structuring interactive programs and managing unexpected inputs logically
Concept 1.5: Loops
- For Loops
- While Loops
- Range & Len
- Breaks
- Problem Set 1.9
Concept 1.6: Exceptions
- Try & Exceptions
- Problem Set 1.10
Mini-Project 1.3: Word Analyzer
- App checks word counts (total count, specific words/letters) of user-inputted sentences.
- Gain mastery of for and while loops
- Learn when exceptions are handy
Concept 1.7: Functions
- Function Syntax
- Returns
- Arguments
- Positional Arguments
- Keyword Arguments
- Default Arguments
- Variable-Length Arguments (*args)
- Variable-Length Keyword Arguments (**kwargs)
- Positional-Only Arguments (/)
- Keyword-Only Arguments (*)
- Order of Combined Types
- Problem Set 1.11
Concept 1.8: Classes & Objects
- Classes Syntax
- Methods
- Self Argument
- Constructor & Destructor Methods (__init__, __del__)
- Instance Methods
- Decorators
- Class Methods (@classmethod)
- Static Methods (@staticmethod)
- Getter, Setter, & Deleter Methods
- Special (Dunder) Methods
- Creating Instances of Objects
- Object-Oriented Programming
- Encapsulation & Abstraction
- Problem Set 1.12
Mini-Project 1.4: Library Management System
- Program manages library; users can add/borrow/view available books using functions & a class-based structure.
- Learn how to modularize code via functions
- Gain mastery of object-oriented programming
Section 2 | Essentials of MatPlotLib & Pandas
- Understand data preprocessing!
- Create graphs using PyPlot!
- Understand Pandas DataFrames!
- Complete problem sets!
- Apply preprocessing to mini-projects!
Concept 2.1: PyPlot Basics
- Intro to Data Preprocessing
- Importing a figure
- Figure Titles
- Axes Titles
- Scatter Plots
- Plotting Functions (Line Plots)
- Bar Plots
- Histograms
- Heatmaps
- Problem Set 2.1
Section 3 | Essentials of NumPy
- Learn key functionalities of NumPy!
- Understand how to use NumPy for efficient numerical computations!
- Understand basics of linear algebra!
- Complete problem sets!
Concept 3.1: NumPy Arrays
- Intro to NumPy
- Creating a NumPy Array
- Comparison w/ Python arrays
- Multi-dimensional arrays
- Special NumPy Arrays
- Zero Array
- One Array
- Empty Array
- Ranged Array
- Linspace Array
- Random Array
- Indexing & Slicing Arrays
- Single/Multi-dimensional Indexing
- Advanced Indexing
- Shape Manipulation
- Reshaping
- Flattening
- Transposing
- Broadcasting Rules & Operations
- Problem Set 3.1
Section 4 | Introduction to Machine Learning
- Understand ML & DL!
- Learn fundamental concepts!
Concept 4.1: What is ML?
- Manual Programming vs. Learning
- AI vs. ML vs. DL
- Models
- Training & Testing Data
- Features & Labels
- Generalization
Concept 4.3: Fundamentals of Neural Networks
- Intro to Neural Networks
- Layers
- Activation Functions
- Loss Functions
- Optimization
Section 5 | Essentials of PyTorch
- Learn fundamentals of PyTorch!
- Understand importance of GPUs!
- Create tensors in PyTorch!
- Implement neural networks!
- Complete problem sets!
Concept 5.1: Intro to PyTorch
- What’s PyTorch?
- Applications
- NLP
- Computer Vision
- Tensors
- Dynamic Computational Graphs
- Intro to GPUs
- Check GPU
- Use GPU
Concept 5.3: Neural Network Operations
- Neural Networks (Re)Introduction
- Activation Functions
- ReLU
- Sigmoid
- Tanh
- Linear Layers
- Softmax
- Loss Functions
- Mean Squared Error
- Cross Entropy Loss
- Optimizers
- Gradient Descent
- Stochastic Gradient Descent
- Problem Set 5.2