Training Milestones
Book Counselling Session
Overview:-
• Understanding Machine Learning (ML) as a Framework.
• Exploring Various Variants of ML.
• Supervised Learning .
• Unsupervised Learning .
• Semi-Supervised Learning .
• Introduction to Deep Learning as a Sub-field of ML .
Overview:-
• Introduction to Linear Regression.
• Principles and Applications in Predictive Modelling .
• Logistic Regression.
• Understanding Binary Classification Problems .
Model Architecture:
• Components of ML Model Architecture.
• Cost/Loss Function.
• Error Metric .
• Optimizer .
• Overview of Decision Trees, Random Forests, and Support Vector Machines (SVMs) in Supervised
Learning.
Understanding Neural Networks:
• Deep Dive into Feedforward Neural Networks (FFNNs).
• Architecture and Key Concepts .
• Implementing Neural Networks from Scratch in Python.
• Using NumPy, TensorFlow, PyTorch, and JAX .
Sequence-to-Sequence Tasks:-
• Introduction to Recurrent Neural Networks (RNNs) and their applications.
• Understanding Long Short-Term Memory (LSTM) Networks for Handling Temporal Data.
• Overview of Transformer Architecture and its Role in NLP
Generative AI Overview:-
• Exploring the Concept of Generative Adversarial Networks (GANs) and their applications .
• Understanding Transformer Architecture and Diffusion Models.
1. Introduction to Vector Databases