The Complete Course for Generative AI for RPA

Learn to set up python projects in VS Code, create and activate conda environments with Python 3.12, run py files and ipi kernel enabled Jupyter notebooks, and manage kernels.

Learn Python basics by exploring syntax and semantics, including single- and multi-line comments, case sensitivity, indentation, line continuation, and variable assignment with type inference.

learn to declare and assign variables in python, naming conventions, and understand types like int, float, string, boolean, dynamic typing with type conversion using input, print, int(), float(), and str().

Learn how to perform arithmetic, comparison, and logical operations in Python with practical examples, including addition, subtraction, multiplication, division, flow division, modulus, exponential, and a calculator project.

Explore lists in Python within the complete course for Generative AI for RPA to understand how to use Python lists.

Explore Python tuples: learn to create, access, pack and unpack, and use tuple operations, while understanding immutability, nesting, and practical uses in data structures and function arguments.

Explore real world python list use cases, from a to-do list and inventory management to student grades and user feedback, using append, remove, and in checks.

Learn to define and call functions in Python, cover syntax, parameters (default, positional, keyword, variable length), return statements, and practical examples.

Apply the map function to every item in an iterable, returning a map object for concise transformation, with examples like square, lambda, multiple iterables, and converting strings to integers.

Explore the Python filter function, which creates an iterator from iterables by applying a condition, with practical examples using lists, dictionaries, and a lambda function for data cleaning.

Learn how to import modules and packages in Python, use built-in math and NumPy functions, install packages, and create custom packages with __init__.py and subpackages.

Explore Python's standard library overview, demonstrating array, math, random, os, json, csv, datetime, time, and regex usage with practical examples.

Learn to perform file operations in Python by reading and writing text and binary files, using with open, handling line by line reads, appending, and seeking to reset the cursor.

Master working with file paths using the os module to create directories, list files, and join paths. Learn to verify existence and differentiate files and directories with is_file and is_dir.

Explore classes and objects in Python to model real world entities with object oriented programming, using __init__ and self to define attributes and methods.

Learn how single and multiple inheritance work in Python, using car and Tesla examples to show how parent classes provide attributes and methods to children.

Explore polymorphism in Python's object-oriented programming, focusing on method overriding, interfaces and abstract base classes, with practical shape and animal examples.

Explore encapsulation in Python: bundle data and methods, restrict access with public, protected, and private variables, and use getter and setter methods to manage private state in Python's object-oriented programming.

Explore Python's magic methods, known as dunder methods, and how they define an object's behavior for built-in operations. See examples like __init__, __str__, and __repr__ and learn to override them.

Explore operator overloading in Python by overriding magic methods like __add__, __sub__, __mul__, __truediv__, and __eq__ within a vector class to customize arithmetic and comparisons.

Learn to implement custom exceptions in Python by creating a generic error and a date of birth exception, then raise and handle them with try-except while validating age in form.

Explore getting started with Streamlit to build interactive web apps for machine learning and data science using Python, including widgets, data frames, charts, and CSV uploads.

Build an end-to-end machine learning app with streamlit, loading iris data via sklearn, training a random forest classifier, and deploying interactive sliders to predict species.

Explore the NLP roadmap from text preprocessing to transformers, using Python, NLTK, and spaCy. Learn vectorization techniques like bag of words, tf-idf, and word2vec for applications such as spam classification.

Explore text preprocessing with NLTK stemming techniques, including Porter, regex, and Snowball stemmers, their benefits and limitations, and compare to lemmatization in natural language understanding.

Apply bag of words with NLTK to a spam dataset, including cleaning, stop-word removal, and Porter stemming. Convert text to vectors with count vectorizer, max_features and binary bag of words.

Explore NLP in deep learning, from sequential data and neural networks to RNNs, LSTMs, GRUs, and CNNs. Learn encoders, decoders, self-attention, transformers, and how these enable generative AI and LLMs.

Learn how MLOps integrates DevOps principles with the machine learning lifecycle, using version control, automated pipelines, CI/CD, and monitoring to enable collaboration and reliable, scalable model deployment.

Set up an end-to-end deep learning project using TensorFlow and Keras to build a binary churn classification model, perform feature engineering, and deploy with pickle or h5 via streamlet.

Encode categorical features with label and one-hot encoding, scale data, and split into train and test, saving encoders and scaler with pickle to prepare an ANN workflow.

Load trained ann model and pickle files, transform input data with one-hot encoding for geography and label encoding for gender, apply scaling, and predict churn probability.

Build an end-to-end streamlit app that loads a trained ANN model with pickled encoders and scalers to predict customer churn in real time.

Build an ANN regression model for salary prediction, detailing data preprocessing, label encoding, one-hot encoding, scaling, train-test split, training with early stopping, evaluation, and streamlit deployment.

Determine the optimal number of hidden layers and neurons in an artificial neural network using grid search, cross validation, and heuristics with keras classifier.

Develop an end-to-end sentiment analysis model using a simple RNN on IMDB reviews, with embedding layers and word embeddings for feature representation, deployed via streamlit.

Learn to implement word embedding with keras and tensorflow by converting words to indices, using an embedding layer, and padding sentences to a fixed length for RNN training.

Build and deploy an end-to-end Streamlit web app for IMDb sentiment analysis, integrating a trained simple RNN with an h5 model and live predictions.

Explore the LSTM RNN architecture, including forget gate, input gate and candidate memory, and the output gate, plus the memory cell that blends short-term and long-term memory.

Explore how the forget gate in LSTM RNN uses the previous hidden state and current input to produce f(t) and gate CT-1, controlling memory.

Explore how a long short-term memory network uses forget, input, and output gates to train on restaurant text, converting words to vectors with word2vec and updating memory.

Analyze variants of LSTM RNN, highlighting forget and input gates, memory cell and candidate memory, peephole connections, and coupled gate designs, and introduce GRU as another recurrent unit.

Explore building an end-to-end next-word predictor with LSTM and GRU, from Shakespeare Hamlet corpus data collection to deployment via a streamlet app.

Collect input data from NLTK's Gutenberg Shakespeare Hamlet; preprocess with tokenizer, text-to-sequence, padding, and then split into train and test for an LSTM RNN.

train a multi-layer lstm rnn with embedding, dropout, and dense softmax output, compile with categorical cross-entropy and adam, and fit on x-train and y-train to improve accuracy.

Learn to build an LSTM-based next-word predictor with tokenization and padding, and save the model and tokenizer for a streamlet app.

Implement this project with a GRU variant, replacing LSTM in the layers, train it, and compare accuracy, noting GRU has fewer gates.

Explore how bidirectional RNNs leverage forward and backward context to improve NLP predictions, contrasting simple RNNs, LSTMs, and GRUs, with language translation and one-to-many and many-to-many tasks.

Explore the problems with encoder-decoder sequence-to-sequence models, where a single context vector fails on long sentences, lowering blue scores. Learn how attention mechanisms and architecture changes address this.