Week Start Date End Date Topic

1 2024-06-01 2024-06-07 Introduction to AI and ML (Java Context

2 2024-06-08 2024-06-14 Linear Algebra Review
3 2024-06-15 2024-06-21 Probability & Statistics
4 2024-06-22 2024-06-28 Basic ML Algorithms
5 2024-06-29 2024-07-05 Regression with Smile
6 2024-07-06 2024-07-12 Classification with Smile
7 2024-07-13 2024-07-19 Clustering with Smile
8 2024-07-20 2024-07-26 Data Preprocessing
9 2024-07-27 2024-08-02 Model Evaluation & Tuning
10 2024-08-03 2024-08-09 Neural Network Theory
11 2024-08-10 2024-08-16 NN from Scratch (Forward Pass)
12 2024-08-17 2024-08-23 Java DL Frameworks Overview
13 2024-08-24 2024-08-30 Deep Java Library (DJL) Basics
14 2024-08-31 2024-09-06 DJL Transfer Learning
15 2024-09-07 2024-09-13 DJL Inference Service
16 2024-09-14 2024-09-20 DJL Performance Testing
17 2024-09-21 2024-09-27 Deeplearning4j (DL4J) Basics
18 2024-09-28 2024-10-04 DL4J GPU Acceleration
19 2024-10-05 2024-10-11 DL4J Hyperparameter Tuning
20 2024-10-12 2024-10-18 DL4J Model Deployment
21 2024-10-19 2024-10-25 NLP with Apache OpenNLP
22 2024-10-26 2024-11-01 Custom NER Model
23 2024-11-02 2024-11-08 Stanford CoreNLP – Parsing & Sentimen
24 2024-11-09 2024-11-15 NLP Service via REST
25 2024-11-16 2024-11-22 RL Basics (Q-Learning)
26 2024-11-23 2024-11-29 RL Algorithms (SARSA)
27 2024-11-30 2024-12-06 RL Environment & Reward Shaping
28 2024-12-07 2024-12-13 RL Service API
29 2024-12-14 2024-12-20 Microservices Architecture
30 2024-12-21 2024-12-27 CI/CD Pipeline
31 2024-12-28 2025-01-03 Dashboard & Visualization
32 2025-01-04 2025-01-10 Cloud Deployment & Monitoring
 Learning Objectives
Understand AI vs ML vs DL, Java’s role and ecosystem
Master vectors, matrices, eigenvalues/vectors in ML context
Understand distributions, Bayes theorem, mean/variance, hypothesis testi
Implement linear regression and k-NN from scratch
Train and evaluate regression models (OLS, Ridge)
Build decision tree, SVM, k-NN classifiers
Implement k-means, DBSCAN and evaluate clusters
Handle missing values, normalization, encoding
Cross-validation, grid/random search, ROC curves
Learn perceptrons, backpropagation, activations
Implement feedforward calculations
Survey DL4J, DJL, Tribuo
Set up DJL and train basic CNN
Fine-tune pretrained models
Serve model via REST
Benchmark inference latency
Build MLP and CNN
Configure CUDA backend
Use Arbiter for tuning
Containerize and deploy model
Tokenization, POS, NER
Train NER on custom data
Use CoreNLP for parsing & sentiment
Expose NLP pipeline as API
Understand Q-Learning algorithm
Implement SARSA
Design custom env and reward
Serve RL agent decisions
Design microservices for AI
Set up automated CI/CD
Create web dashboard for analytics
Deploy to cloud; set up monitoring
 Study Resources (Links)
1. https://www.coursera.org/learn/ai-for-everyone
2. https://learning.oreilly.com/library/view/artificial-intelligence-with/9781787126053/
https://www.coursera.org/learn/linear-algebra-machine-learninghttps://www.khanacademy.org/math/linear-algebra
https://www.khanacademy.org/math/statistics-probabilityhttps://www.educative.io/courses/probability-for-machine-learnin
https://www.coursera.org/learn/machine-learninghttps://github.com/SpencerPark/IJava
https://haifengl.github.io/quickstart.htmlhttps://www.udemy.com/course/java-machine-learning-smile/
https://haifengl.github.io/classification.html
https://haifengl.github.io/clustering.html
https://www.cs.waikato.ac.nz/ml/weka/;https://commons.apache.org/proper/commons-csv/
https://haifengl.github.io/evaluation.htmlhttps://www.cs.waikato.ac.nz/ml/weka/
https://www.coursera.org/specializations/deep-learninghttps://www.educative.io/courses/neural-networks-from-scratch
https://www.educative.io/courses/neural-networks-from-scratch
https://deeplearning4j.konduit.ai/quickstarthttps://djl.ai/docs/
https://djl.ai/docs/quick_start.htmlhttps://www.udemy.com/course/deep-learning-java-djl/
https://github.com/deepjavalibrary/djl-model-zoo
https://djl.ai/docs/quick_start.htmlhttps://spring.io/projects/spring-boot
https://github.com/openjdk/jmhhttps://gatling.io/docs/
https://deeplearning4j.konduit.ai/quickstarthttps://github.com/eclipse/deeplearning4j-examples
https://deeplearning4j.konduit.ai/nd4j/backend-gpu
https://deeplearning4j.konduit.ai/arbiter
https://spring.io/projects/spring-boothttps://www.docker.com/
https://opennlp.apache.org/docs/1.9.3/manual/opennlp.htmlhttps://www.udemy.com/course/natural-language-processing-i
https://opennlp.apache.org/docs/1.9.3/manual/opennlp.html
https://stanfordnlp.github.io/CoreNLP/
https://spring.io/projects/spring-boot
https://github.com/chen0040/java-reinforcement-learninghttps://www.udemy.com/course/artificial-intelligence-iv-reinforce
https://github.com/chen0040/java-reinforcement-learning
https://learning.oreilly.com/library/view/reinforcement-learning/9780262039246/
https://spring.io/projects/spring-boot
https://spring.io/projects/spring-cloudhttps://www.udemy.com/course/docker-kubernetes-the-complete-guide/
https://docs.github.com/actionshttps://www.educative.io/courses/cicd-java-microservices
https://reactjs.org/https://www.thymeleaf.org/
https://aws.amazon.com/https://prometheus.io/https://grafana.com/
 Project Project Description
AI Use Case Research Research 3 AI/ML use cases and present how Java technologies can implement
Linear Algebra Module Implement vector/matrix classes with operations in Java
Java Stats Library Create utilities for basic statistical functions and simulate distributions
Mini ML Library Develop fit/predict for LinearRegression and KNearestNeighbors
House Price Predictor Use Smile to build regression on housing dataset
Customer Churn ClassifierPredict churn using Smile classification
Customer Segmentation Cluster customer data and analyze segments
Preprocessing Pipeline Build Java module for data cleaning and transformation
Hyperparameter Tuner Implement CV-based hyperparameter search
ANN Visualizer JavaFX app visualizing layers and weights
Feedforward NN Manual forward pass implementation
Frameworks Benchmark Compare training on small dataset
DJL CNN Classifier Classify CIFAR-10 images
ResNet Fine-Tune Adapt ResNet on custom dataset
Image Classification API REST endpoint for image inference
Inference Benchmark Load-test service latency
DL4J MNIST Classifier Train CNN on MNIST
GPU Model Training Speed up training with GPU
Tuned MNIST Model Optimize hyperparameters
DL4J Service Docker Compose multi-instance
Text Preprocessing Build pipeline for token & sentence detection
NER Training Train and evaluate NER model
Sentiment Analysis Integrate sentiment scoring
NLP REST Service Create REST endpoints for NLP
GridWorld Agent Implement Q-learning in grid-world
SARSA Agent Train agent using SARSA
Env Design Implement custom RL environment
RL REST API Expose agent via REST
Architecture Blueprint Document microservices design
CI/CD Implementation Implement GitHub Actions workflow
Analytics Dashboard Develop UI with charts
Cloud Deployment Deploy platform and configure alerts
 Libraries/Tools to Use Expected Outcome
N/A Research document or slide deck
Apache Commons Math Test suite validating operations
Apache Commons Math CLI tool demonstrating functions
Pure Java, JUnit Models with ≤5% error on test sets
Smile, Apache Commons CSV Model R² ≥0.7
Smile Accuracy ≥75%
Smile Silhouette score ≥0.5
Weka, Apache Commons CSV Reusable preprocessing library
Smile, Weka Improved model performance logs
JavaFX Interactive NN demo
Pure Java Console outputs match expected
DL4J, DJL Report performance comparison
DJL Accuracy ≥60%
DJL Improved accuracy
DJL, Spring Boot API returns predictions
JMH, Gatling Latency <200ms
DL4J Accuracy ≥95%
DL4J, CUDA ≥50% speed gain
DL4J Arbiter Higher accuracy
Docker, Spring Boot Scalable service
OpenNLP Accurate text parsing
OpenNLP F1-score ≥85%
CoreNLP Sentiment accuracy ≥80%
Spring Boot, OpenNLP/CoreNLPFunctional NLP API
Java RL Library Agent learns optimal policy
Java RL Library Agent converges
Pure Java Env runs episodes
Spring Boot, Java RL Library API returns actions
Spring Cloud Approved blueprint
GitHub Actions, Docker Pipeline passes builds
React or Thymeleaf, Chart.js Functional dashboard
AWS/GCP, Prometheus, Grafan Live system with metrics