Deep Learning Architect Internship
Duration: 4 Weeks
Project Training – Offline / Online
Program Summary:
- Covers Python, data analysis, machine learning, and deep learning concepts.
- Hands-on labs using tools like Pandas, Scikit-learn, and TensorFlow/Keras.
- Focus on real-world problem-solving and end-to-end ML/DL workflows.
- Includes capstone projects such as image classification and sentiment analysis.
- Emphasizes practical skills, model tuning, and final project presentation.
Program Outcomes:
- Gains a solid understanding of core data analysis, machine learning, and deep learning principles.
- Build practical skills using Python, Pandas, Scikit-learn, TensorFlow/Keras, and Jupyter Notebook.
- End-to-End Project Development Skills to handle real-world datasets, build and evaluate models, and deliver complete ML/DL projects.
- Portfolio-Ready Capstone Projects complete and present impactful projects
Project stream:
- Apply machine learning algorithms like SVM, Random Forest, and K-Means to real-world datasets.
- Implement complete ML pipelines: preprocessing, modeling, and evaluation.
- Focus on feature CNN,ANN,GRU,
- Deploy final models using Streamlit and version control with GitHub.
Platform:
- Python 3.x, NumPy, Pandas, Matplotlib, Seaborn, Scikit-learn
- Jupyter Notebook, VS Code, Google Colab
| Days 1–15: Theory + Simulation Labs | ||
| Day | Topic | Details |
|---|---|---|
| Day 1 | Python for AI/ML | NumPy, Lists, Functions, Loops |
| Day 2 | Introduction to DAV (Data Analysis & Visualization) | Load data, describe, visualize using matplotlib & seaborn |
| Day 3 | Pandas for Data Analysis | Series, DataFrames, slicing, filtering |
| Day 4 | Data Cleaning & Preprocessing | Missing values, outliers, encoding, scaling |
| Day 5 | Exploratory Data Analysis (EDA) | Correlations, pairplots, histograms, boxplots |
| Day 6 | Feature Engineering & Selection | Feature extraction, PCA, multicollinearity |
| Day 7 | Intro to Machine Learning | Supervised vs Unsupervised, use cases |
| Day 8 | Regression Models | Linear, polynomial regression + RMSE, R² |
| Day 9 | Classification Algorithms | Logistic Regression, KNN, Decision Trees |
| Day 10 | Model Evaluation & Tuning | Confusion matrix, accuracy, precision, recall |
| Day 11 | Introduction to Neural Networks | Perceptron, activation functions, loss |
| Day 12 | Deep Learning with TensorFlow/Keras | Building a simple NN using Keras Sequential |
| Day 13 | Convolutional Neural Networks (CNNs) | Image classification (MNIST or CIFAR-10) |
| Day 14 | Recurrent Neural Networks (RNNs) & LSTMs | Time series, text prediction |
| Day 15 | Regularization & Model Optimization | Dropout, EarlyStopping, Model saving/loading |
| Days 16–20: Final ML Project | ||
| Day 16 | Problem Definition & Dataset Selection | Finalize dataset, define project scope |
| Day 17 | Data Preprocessing & EDA | Clean, visualize and prepare the dataset |
| Day 18 | Model Building | Train ML/DL model, tune hyperparameters |
| Day 19 | Testing & Evaluation | Metrics, confusion matrix, plots |
| Day 20 | Final Demo & Report Submission | Present project, submit code & documentation |
| End to End Projects | ||
| Image Classifier, Home Energy Consumption Forecasting, Object Detection | ||
