INTRODUCTION TO NLP & Deep Learning 4
- Understanding Textual DataLecture1.1
- What is Natural Language Processing?Lecture1.2
- Industry applications of NLPLecture1.3
- Machine Learning vs NLP vs Deep LearningLecture1.4
PART A – Natural Language Processing 1
Introduction to NLP 4
- Areas of applicationLecture3.1
- Understanding textLecture3.2
- Text encodingLecture3.3
- Regular ExpressionsLecture3.4
Basic Text Pre-Processing 5
- Bag of Words.Lecture4.1
- TokenizationLecture4.2
- StemmingLecture4.3
- LemmatizationLecture4.4
- Count vectorizer vs TF-IDF vectorizerLecture4.5
Advanced Lexical Processing 5
- Phonetic HashingLecture5.1
- Distance calculationLecture5.2
- Levenshtein DistanceLecture5.3
- SoundexLecture5.4
- Mutual InformationLecture5.5
Introduction to syntactic processing 6
- What and why of syntactic processingLecture6.1
- ParsingLecture6.2
- Parts-of-Speech taggingLecture6.3
- Different approaches of POS taggingLecture6.4
- Hidden Markov ModelsLecture6.5
- Stochastic ParsingLecture6.6
Parsing 5
- Limitations of shallow parsingLecture7.1
- Constituency Free Demo GrammarsLecture7.2
- Top Down parsingLecture7.3
- Bottom up parsingLecture7.4
- Dependency ParsingLecture7.5
Information Extraction 6
- Introduction to IELecture8.1
- Rule based modelsLecture8.2
- Named Entity RecognitionLecture8.3
- Shallow algorithm for NERLecture8.4
- Probabilistic models for NERLecture8.5
- Conditional Random FieldsLecture8.6
Semantic Processing 5
- Entities and TypesLecture9.1
- Schema and knowledge graphsLecture9.2
- AssociationsLecture9.3
- WordNet and Concept NetLecture9.4
- Lesk AlgorithmLecture9.5
Advanced Semantics 8
- Distributional SemanticsLecture10.1
- Occurrence & Co-occurrence matrixLecture10.2
- Word EmbeddingsLecture10.3
- LSA & PLSALecture10.4
- Skip gramsLecture10.5
- Word2Vec and GloveLecture10.6
- Topic ModellingLecture10.7
- Latent Dirichlet AllocationLecture10.8
PART B – DEEP LEARNING 1
Introduction to Deep Learning 5
- Introduction to Deep LearningLecture12.1
- Machine Learning vs Deep LearningLecture12.2
- What is unstructured data?Lecture12.3
- Industry applications of Deep LearningLecture12.4
- Prerequisites for being Deep Learning expertLecture12.5
Artificial Neural Networks 5
- How human brain works?Lecture13.1
- Inspiration to Artificial Neural NetworksLecture13.2
- Introduction to PerceptronLecture13.3
- Binary & Multi classification using PerceptronLecture13.4
- How artificial neuron works?Lecture13.5
Structure of Artificial Neural Networks 5
- Different layers in Neural NetworksLecture14.1
- Parameters and Hyper parameters in ANN’sLecture14.2
- Activation FunctionsLecture14.3
- Assumptions of ANN’sLecture14.4
- Representation of Text, Images, Videos in ANN’sLecture14.5
Feed Forward & Backpropagation 6
- Weights and Bias calculationLecture15.1
- Information flow between layersLecture15.2
- Feedforward algorithmLecture15.3
- Calculating Loss functionLecture15.4
- Updating weights and biasLecture15.5
- Chain rule of back propagationLecture15.6
Tuning the Neural Networks 7
- OptimizersLecture16.1
- RegularizationLecture16.2
- DropoutsLecture16.3
- Batch NormalizationLecture16.4
- Gradient DescentLecture16.5
- Number of layersLecture16.6
- Time taken to train a neural networkLecture16.7
Convolutional Neural Networks 9
- Introduction to CNNLecture17.1
- Reading image dataLecture17.2
- Data augmentationLecture17.3
- What is convolution?Lecture17.4
- FiltersLecture17.5
- Striding and PaddingLecture17.6
- Pooling layersLecture17.7
- Activation functionsLecture17.8
- Feature extractionLecture17.9
CNN Architectures 8
- Overview of different architectures in CNNLecture18.1
- VGG NetLecture18.2
- ResNetLecture18.3
- Inception and GoogleNetLecture18.4
- Transfer LearningLecture18.5
- Use cases of Transfer learningLecture18.6
- Object detectionLecture18.7
- Case Study – Classify images using Transfer LearningLecture18.8
Recurrent Neural Networks 7
- Introduction to sequence modelsLecture19.1
- Architecture of Recurrent networksLecture19.2
- Types of RNN’sLecture19.3
- Feedforward approach in RNNLecture19.4
- Backpropagation Through TimeLecture19.5
- Vanishing & Exploding gradients in RNN’sLecture19.6
- Word EmbeddingsLecture19.7
RNN architectures 4
- Bidirectional RNN’sLecture20.1
- Gating mechanismLecture20.2
- Long Short-Term Memory (LSTM)Lecture20.3
- Gated Recurrent Units (GRU)Lecture20.4
GAN & Auto Encoders 6
- Introduction to Generative Adverbials NetworksLecture21.1
- How GAN’s work?Lecture21.2
- Image generation using GAN’sLecture21.3
- Industry use cases on GAN’sLecture21.4
- Autoencoders (standard, denoising, contractive)Lecture21.5
- Variational Auto EncodersLecture21.6
Reinforcement Learning 7
- Introduction to RLLecture22.1
- Agent-EnvironmentLecture22.2
- Actions & PoliciesLecture22.3
- Exploration and ExploitationLecture22.4
- State Value Function & Action Value functionLecture22.5
- Policy iteration & ImprovementsLecture22.6
- Monte Carlo & Q-Learning methodsLecture22.7
Resume Preparation Tips 0
No items in this sectionInterview Guidance and Support 0
No items in this section
This content is protected, please login and enroll course to view this content!
