Batch GD vs Mini Batch GD vs SGD | Codebasics

Go to Course Page

Gen AI & DS Bootcamp is Live

0% Completed

- Login
- Register

back

- Login
- Register

0% Completed

Contents

1.1: Deep Learning and Your Career
1.2: The AI family tree
1.3: Pre-requisites
1.4: System Requirements
1.5: Course Overview

2.1: Join Discord for Doubt Clearing Support & Networking
2.2: Setting Video Resolution and Video Speed Globally

3.1: Neural Networks: The Foundation of Deep Learning
3.2: Deep Learning vs Statistical ML: When to Use What?
3.3: Neural Network Architectures
3.4: Real World Applications of Deep Learning
3.5: Tooling: PyTorch vs Tensorflow
3.6: Tooling: GPU, TPU
3.7: Quiz
3.8: Chapter Summary

4.1: What is Neuron?
4.2: Perceptron and Multilayer Perceptron (MLP)
4.3: Neural Network Intuition: Insurance Prediction
4.4: The Purpose of Activation Function
4.5: Activation Functions: Sigmoid, ReLU, Tanh, SoftMax
4.6: Quiz
4.7: Chapter Summary

5.1: PyTorch Installation
5.2: Matrix Fundamentals
5.3: PyTorch Tensor Basics 1
5.4: PyTorch Tensor Basics 2
5.5: Derivative and Partial Derivative
5.6: Chain Rule
5.7: Autograd in PyTorch
5.8: Numpy Arrays vs PyTorch Tensors
5.9: Quiz
5.10: Exercise
5.11: Chapter Summary

6.1: Training through Backpropagation
6.2: Gradient Descent: Theoretical Foundation
6.3: Gradient Descent: PyTorch Implementation
6.4: Batch GD vs Mini Batch GD vs SGD
6.5: Mini Batch GD and SGD: PyTorch Implementation
6.6: Quiz
6.7: Exercise
6.8: Chapter Summary

7.1: Employee Bonus Prediction
7.2: Datasets and DataLoaders
7.3: Handwritten Digits Classification
7.4: Classification Report and Confusion Matrix
7.5: Cost Function: Binary Cross Entropy (a.k.a. Log Loss)
7.6: Cost Function: Cross Entropy
7.7: Quiz
7.8: Exercise
7.9: Chapter Summary

8.1: Model Optimization Overview
8.2: Exponentially Weighted Moving Average
8.3: Gradient Descent with Momentum
8.4: RMSprop
8.5: Adam
8.6: Optimizers in Action with Fashion MNIST
8.7: Quiz
8.8: Exercise
8.9: Chapter Summary

9.1: What is Regularization?
9.2: Dropout Regularization
9.3: L1, L2 Regularization
9.4: Batch Normalization
9.5: Early Stopping
9.6: Quiz
9.7: Exercise
9.8: Chapter Summary

10.1: What is Hyperparameter Tuning?
10.2: GridSearchCV, RandomSearchCV
10.3: Optuna
10.4: Quiz
10.5: Exercise
10.6: Chapter Summary

11.1: What is CNN? Convolution, Kernels, Pooling and Beyond
11.2: Padding and Strides
11.3: CIFAR10 Image Classification using CNN
11.4: Data Augmentation
11.5: Transfer Learning
11.6: Pre-trained Models – ResNet, EfficientNet, MobileNet etc.
11.7: Caltech101 Classification Using Transfer Learning
11.8: Quiz
11.9: Exercise
11.10: Chapter Summary

12.1: Sequence Models
12.2: RNN in Depth
12.3: Types of RNN
12.4: Vanishing Gradient Problem
12.5: LSTM
12.6: GRU
12.7: Quiz
12.8: Chapter Summary

13.1: Introduction to Transformer Architecture
13.2: Word Embeddings
13.3: Contextual Embeddings
13.4: Overview of Encoder and Decoder
13.5: Tokenization, Positional Embeddings
13.6: Attention Mechanism
13.7: Multi Headed Attention
13.8: Decoder
13.9: How Transformers are Trained?
13.10: Hugging Face: BERT Basics
13.11: Hugging Face: Spam Classification Using BERT
13.12: Hugging Face: Next Word Prediction Using GPT2
13.13: Quiz
13.14: Exercise
13.15: Chapter Summary

14.1: AtliQ AI’s First Big Client: Vroom Cars
14.2: Problem Statement & SOW
14.3: Data Load and Transformation
14.4: Model Training with CNN
14.5: Model Training with CNN and Regularization
14.6: Model Training using Transfer Learning
14.7: Hyperparameter Tunning using Optuna
14.8: Model Evaluation and Export
14.9: Streamlit App
14.10: FastAPI Server

15.1: Quiz

Instructor

Dhaval Patel

Dhaval Patel

Data Entrepreneur | YouTuber | Ex - Bloomberg, Nvidia

I have 17 years of experience in Programming and Data Science working for big tech companies like NVIDIA and Bloomberg. I also run a famous YouTube channel called Codebasics where I pursue my passion for teaching. Codebasics is one of the top channels on YouTube when it comes to data science, machine learning, data structures, etc. I firmly believe that “Anyone can code” and I use analogies, simple explanations, and step-by-step storytelling to explain difficult concepts in such a way that even a high school student can understand them easily.

Batch GD vs Mini Batch GD vs SGD

Prev Next

Lecture content Locked

Enroll in Course to Unlock

Login

Log in with Google

Log in with Linkedin

E-Mail Address

Enter your Password

Forgot Password?

Don't have an account? Register Now!

By signing up, you agree to
our Terms and Conditions and Privacy Policy.