DEEP LEARNING SUMMER INTERNSHIP PROGRAM 2022
- DEEP LEARNING
COMPLETE TRAINING ON TECHNOLOGY | PROJECT DEVELOPEMENT
MANOJ: +91 9676190678
407, 4th Floor, Pavani Prestige (R.S Brothers)Building, Ameerpet, Hyderabad, India Opposite Image Hospital & Beside KLM Fashion Mall.
About Deep Learning
Deep learning is an artificial intelligence function that imitates the workings of the human brain in processing data and creating patterns for use in decision making. Deep learning is a subset of machine learning in artificial intelligence (AI) that has networks capable of learning unsupervised from data that is unstructured or unlabeled. Also known as deep neural learning or deep neural network. Deep learning has evolved hand-in-hand with the digital era, which has brought about an explosion of data in all forms and from every region of the world.
Day - 1: Introduction to Machine Learning & Deep Learning
Diffenrence between Machine and Deep Learning
How Deep Learning Useful in Daily Life
Deep Learning Goals and Deliverables.
Why Deep Learning
Deep Learning Tools.
Day - 2: Introduction to Python
2.Anaconda Installation and Introduction to Jupyter Notebook
Day - 3: Python Basics
Day - 4: Python Baiscs
Day - 5: Python Baiscs
Day - 6: Python for Data Science - Numpy
2. Operations in Numpy
Day - 7: Python for Data Science - Pandas
2. Operations in Pandas – Pandas Basics, Indexing and selecting Data,Merge and Append, Grouping and Summarizing, Lambda functions and Pivot tables
3. Introduction to Reading.
Day - 8: Python for Data Science - Matplotlub
2. Types of plots with Examples
Day - 9: Introduction to SQL
2. Basics of SQL, Data Retrieval, sorting, compound functions and relational operators, pattern matching with wild cards.
3. Basics on Table creation, updating, modifying etc.
4. Overall Structure of data retrieval queries, Merging tables, User Defined Functions (UDF), Frames.
Statistics & Exploratory Data Analysis (EDA)
Day - 10: Introduction to Data Analytics
2. CRISP-DM Framework – Data Preparation, Modelling, Evaluation and Deployment
Day - 11: Data Visualization in Python
2. Introduction to various charts
3. Data visualization toolkit in Python (Libraries or modules available in Python)
4. Plotting Data in Python using matplotlib and seaborn – Univariate Distributions, Bi-variate Distributions
5. Plotting Time series data
Day - 12: Exploratory Data Analysis
2. Data Cleaning – Fixing rows and columns, Missing value Treatment, standardizing values, handling invalid values, Filtering data
3. Data types – Numerical, Categorical (ordered and unordered)
4.Derived Metrics and Feature Engineering
5. Identify Outliers and Handling
Day - 13: Inferential Statistics
2. Discrete and Continuous Probability Distributions
3. Central Limit Theorem – Introduction and Industrial applications
Machine Learning - I
Day - 14: Introduction to Machine Learning
2. Simple Linear Regression
3. Multiple Linear Regression
Day - 15: Logistic Regression
2. Binary classification using univariate logistic regression
3. Maximum Likelihood function, Sigmoid Curve and Best Fit
4. Intuition of odds and log-odds
5. Feature selection using RFE
6. Model evaluation – Confusion Matrix and Accuracy
7. Why Accuracy is not Enough and introduction to sensitivity, specificity, precision, recall, area under curve
8. Logistic Regression Case Study
Day - 16: unsupervised Learning:Clustering
1. Understanding clustering with practical examples
2. KMeans Clustering – understanding the algorithm
3. Practical consideration for KMeans Clustering – Elbow curve, silhouette metric and hopkings test for clustering tendency of data, impact of outliers
1. Hierarchical clustering Algorithm
2. Interpreting the dendogram and Types of Linkages
3. Comparison of Kmeans clustering and Hierarchical clustering – advantages and disadvantages
Machine Learning - II
Day - 17: Support Vector Machine Algorithm
1. Introduction to SVM and How does it works.
2. Advantages and Disadvantages of SVM
3. Kernal Functions in used in SVM
4. Applications of SVM
5. Implementation of SVM using Python
Day - 18: K Nearest Neighbors and Naive Bayes Algorithm
1. Introduction to KNN and How does it works.
2. Advantages and Disadvantages of KNN
3. Applications of KNN
4. Implementation of KNN using Python
1. Intoduction to Naive Bayes
2. Advantage and Disadvantage of Naive Bayes
3. Applications of Naive Bayes
4. Implementation of Naive Bayes using Python
Day - 19: Tree Models
1. Introduction to decision trees and Interpretation
2. Homogeneity measures for splitting a node 1. Gini Index 2. Entropy 3. R2
3. Understanding Hyper parameters – Truncation and Pruning
4. Advantages and Disadvantages
1. Introduction to ensembling, bagging and intuition
2. Random Forest – Introduction and Hyperparamters
3. Building a model using Random Forest
4. Hyper-parameters impact on model and tuning them
5. Importance of predictors using Random Forrest
Day - 20: Deep Learning
Day - 21: Introuction
2. Understanding Deep Learning with the help of a case study.
3. Explore the meaning, process, and types of neural networks with a comparison to human neurons
4. Identify the platforms and programming stacks used in Deep Learning
Day - 22: Perceptron
2. Implement logic gates with Perceptron.
3. Sigmoid units and Sigmoid activation function in Neural Network
4. ReLU and Softmax Activation Functions.
5. Hyperbolic Tangent Activation Function
Day - 23: Artificial Neural Network
2. Implementation of Adaline rule in training ANN.
3. Minimizing cost functions using Gradient Descent rule.
4. Analyze how learning rate is tuned to converge an ANN.
5. Explore the layers of an Artificial Neural Network(ANN).
Day - 24: Multilayer ANN
2. Backpropagation to adjust weights in a neural network.
3. Inspect convergence in a multilayer ANN
4. Implement forward propagation in multilayer perceptron (MLP)
Day - 25: Introduction to TensorFlow
2. Create a computational and default graph in TensorFlow
3. Implement Linear Regression and Gradient Descent in TensorFlow.
4. Application of Layers and Keras in TensorFlow
5. Uses of TensorBoard
Day - 26: Training Neural Networks
2. Optimization & hyperparameters.
3. Solutions to speed up neural networks
4. Regularization techniques to reduce overfitting
Day - 27: Convolutional Neural Networks
2. Implementation of CNNs within Keras
Day - 28: Convolutional Neural Networks
2. Zero padding works with variations in kernel weights
3.Elaborate the pooling concepts in CNNs
Day - 29: Applications of CNN
2. Dense Pridiction
Day - 30: Recurrent Neural Networks
2. Understand the working of recurrent neurons and their layers.
3. Interpret how memory cells of recurrent neurons interact
4. Implement RNN in Keras
5. Demonstrate variable length input and output sequences
Day - 31: Recurrent Neural Networks
2. Implmentation of LSTM RNN using Keras ,
3. Introducntion to GRU and Implementation uisng Keras
4. Introdunction Encoder, Decoder architectures
Day - 32: Memory Models/Networks
2. Introdunction to Dynamic memory networks
3. Introduction to Image Genrative Models
4. GANs, CycleGAN Algotithms
Day - 33: Computer Vision
2. Video to text with LSTM models. Attention models for computer vision tasks.
Day - 34: Natural Language Processing
2. Vector Model Space models of Semantics
3. Word Vector Representation
4. Skip Gram Model
5. Bag of Words Model
Day - 35: Natural Language Processing
2. Applications in word similarity and analogy Recognition
3. Named Entity Recognition.
4. Opinion Mining using RNN
5. Parsing and Setiment Analysis using RNN
6. Sentence Classification using CNN