import tensorflow as tf
from tensorflow import keras

# Learn y = 2x + 1 from examples
x = tf.constant([[0.0], [1.0], [2.0], [3.0], [4.0]])
y = tf.constant([[1.0], [3.0], [5.0], [7.0], [9.0]])

model = keras.Sequential([keras.Input(shape=(1,)), keras.layers.Dense(1)])
model.compile(optimizer=keras.optimizers.SGD(learning_rate=0.05), loss="mse")
model.fit(x, y, epochs=300, verbose=0)
print(model.predict(tf.constant([[10.0]]), verbose=0))   # close to 21

import java.util.List;

public class Averages {
    public static void main(String[] args) {
        List<Integer> marks = List.of(72, 85, 90, 64);
        double avg = marks.stream().mapToInt(Integer::intValue).average().orElse(0);
        System.out.printf("Average: %.1f%n", avg);   // Average: 77.8
    }
}

import tensorflow as tf

# After training a Keras model called `model`:
model.export("exported_model")      # SavedModel format for serving (Keras 3)
# Serving options include TensorFlow Serving (REST/gRPC),
# which any backend — including Java — can call over HTTP.

import java.net.URI;
import java.net.http.*;

public class PredictClient {
    public static void main(String[] args) throws Exception {
        String body = "{\"instances\": [[10.0]]}";
        HttpRequest req = HttpRequest.newBuilder(
                URI.create("http://localhost:8501/v1/models/line:predict"))
            .header("Content-Type", "application/json")
            .POST(HttpRequest.BodyPublishers.ofString(body)).build();
        HttpResponse<String> res = HttpClient.newHttpClient()
            .send(req, HttpResponse.BodyHandlers.ofString());
        System.out.println(res.body());
    }
}
// Assumes a TensorFlow Serving container is running with a model named 'line'

ML path (TensorFlow)
1. Python fundamentals
2. NumPy and pandas
3. Statistics and ML basics with scikit-learn
4. TensorFlow/Keras: tensors, layers, training
5. One image and one text project with proper evaluation
6. Model serving basics

Java path
1. Java syntax and OOP
2. Collections, exceptions, streams
3. SQL and JDBC basics
4. Spring Boot REST APIs
5. Testing with JUnit
6. A deployed backend project

Tick what excites you
☐ Teaching computers to recognise images or text     → TensorFlow / ML
☐ Building reliable systems many users depend on    → Java / backend
☐ Statistics and experiments                         → ML
☐ Clean architecture and design patterns             → Java
Most ticks decide your first path.

Scan 20 job posts
ML / deep learning roles: ____  (skills: Python, TensorFlow/PyTorch, statistics)
Java backend roles: ____         (skills: Java, Spring Boot, SQL)
Entry-level friendly? ML ____ / Java ____
Decide based on interest + local demand.

Six-month plan (pick one)
ML:   Python (1-2) → ML basics (3-4) → TensorFlow projects (5-6)
Java: Core Java (1-2) → SQL + Spring Boot (3-4) → backend projects (5-6)