Weekday Schedule Topic Sub Topic
Day 1 Introduction to Deep Learning / Artificial Intelligence (AIUnderstanding Machine Learning Fundamentals, Limitations of Machine Learning, AI vs ML vs Generative AI,
Day 2 Deep Learning with Keras / Tensorflow Introduction to neural network, ANN architecture, Optimization Techniques
Day 3 ANN Intuition -1 Deep dive into ANN architecture, Hidden layers, Important Parameters of Perceptron, Activation function, Optimizers, Loss Function
Day 4 ANN Intuition -2 Understand Backpropagation, Training of ANN model
Day 5 Image Processing : Introduction to Computer Vision What is Computer Vision?, Read in Images in Python, Basic Image Conversions, Image Resizing, Image Transformations, Contrast Stretching, Introduction to OpenCV
Day 6 Image Processing : CNN Architecture Introduction to CNN architecture, Convolution, Feature detector, Padding, Stride, Activation function, Pooling, Training CNN, Loss function
Day 7 Image Processing : Transfer Learning Transfer learning in image processing ex. Alexnet/VGGnet/InceptionNet/ResNet, Object detection, image/object segmentation
Day 8 OpenCV: Working with Videos Open/Save/Record video using OpenCV, Auto reconnect to video streams, Capturing video using screenshots
Day 9 Advanced CNN Architectures R-CNN, Fast CNN, Faster CNN
Day 10 RNN Intuition -1 Idea behind RNN architecture, Vanishing/Exploding gradient problem, Training of RNN model
Day 11 RNN Intuition -2 LSTM, GRU, RNN vs LSTM vs GRU
Day 12 Text Mining : Using Machine Learning Text pre-processing, Binary weight, BoW, TF-IDF, Spam detection / Sentiments Analysis
Day 13 Text Mining : Using Deep Learning Working with word vectors, Word Embedding, Word2Vec, CBOW/Skip-gram
Day 14 Introduction to Generative AI Descriminative vs Generative models, Generative AI market potential, Generative AI tools
Day 15 Seq2Seq models - 1 (Deep NLP - DNLP) Sequential data analysis, seq2seq model, encoder-decoder architecture, application of seq2seq models
Day 16 Seq2Seq models - 2 (Deep NLP - DNLP) seq2seq model input preparation, model training and testing, seq2seq model tuning
Day 17 Neural Machine Translation (NMT) Understanding Machine Translation, Data Preparation, Building, training and testing Model, Translation Metrics (BLEU Score & BERT Score)
Day 18 GANs and LLM DCGAN - intuition, MNIST dataset, Building the generator, Building the discriminator, Loss (error) calculation, WGAN - intuition
Day 19 Transformer Idea behind transformer, architecture and analysis, pre-trainer models
Day 20 Attention model Attention models, Self-Attention, Scaled Dot-Product Attention, Transformer Block, Multi-Head Attention, Encoder-Decoder Architecture
Day 21 Introduction to Chatbots NLP vs NLU vs NLG, Conventional vs AI Chatbots, Types of Chatbot, Backend architecture
Day 22 Introduction to ChatGPT ChatGPT history, GPT 3.5 vs GPT 4, Backend architecture of ChatGPT
Day 23 Prompt Engineering in ChatGPT What is Prompt Engineering, Prompt Engineering with CETO process, Follow-up Prompts, Prompting Techniques: Zero Shot, One Shot, Few Shot
Day 24 ChatGPT for Data Science GPT for Data Science design principles, GPT to clean data-set, re-organize and perform EDA, GPT for model training and testing
Day 25 ChatGPT for Business and Social media GPT for understanding text, Integrating GPT with email, GPT for email styling, GPT for social media
