3 Days Live Virtual Training on AI and Deep Learning with Python
Artificial Intelligence (AI) and Deep Learning with Python certification course will help you master most popular algorithms such as like CNN, RNN, ANN and more to enhance your skills in Deep Learning and AI with Python.
Duration: 3 Days
Hours: 15 Hours
Training Level: All Level
Batch Ten
Monday, December 09, 2024
11:00 AM - 04:00 PM (Eastern Time)
About Artificial Intelligence (AI) with Python Course:
The AI and Deep Learning with Python Certification course enables you to take your latest skills like AI and Deep Learning into a variety of companies, helping them to apply these techniques to the data and make more informed business decisions. The course covers predictive analytics techniques with the Python language. You will learn about various Python packages like Tensorflow and Keras. This will give you a deep understanding of algorithms like Artificial Neural Networks, Convolutional Neural Networks, and Recurrent neural networks.
Artificial Intelligence (AI) with Python Course Objective:
- Install Python, and Jupyter Notebook, and learn about the various Python packages
- Gain an in-depth understanding of data structure used in Python and learn to import/export data in Python
- Define, understand, and use the various functions in Python
- Learn Python packages like Tensorflow and Keras
- Learn in-depth knowledge of AI and Deep Learning algorithms like ANN, CNN, and RNN and their various used cases.
Who is the Artificial Intelligence (AI) with Python Course Audience?
- This course is meant for all those students and professionals who are interested in using Python's powerful ecosystem
What Basic Knowledge Required to Learn Artificial Intelligence (AI) with Python Course?
- There are no prerequisites
Curriculum
Total Duration: 15 Hours
Introduction to Python
Introduction to Logistic Regression
Introduction to Artificial Neural Network
- History of Neural Networks and Deep Learning
- How do Biological Neurons work?
- Growth of biological neural networks
- Diagrammatic representation: Logistic Regression and Perceptron
- Multi-Layered Perceptron (MLP)
- Notation
- Training a single-neuron model
- Training an MLP: Chain Rule
- Training an MLP: Memoization
- Backpropagation
- Activation functions
- Vanishing Gradient problem
- Bias-Variance tradeoff
Deep Multi-layer perceptrons
- Deep Multi-layer perceptrons:1980s to 2010s
- Dropout layers & Regularization
- Rectified Linear Units (ReLU)
- Weight initialization
- Batch Normalization
- Optimizers: Hill-descent analogy in 2D
- Optimizers: Hill descent in 3D and contours
- SGD Recap
- Batch SGD with momentum
- Nesterov Accelerated Gradient (NAG)
- Optimizers: AdaGrad
- Optimizers: Adadelta andRMSProp
- Adam
- Which algorithm to choose when?
- Gradient Checking and clipping
- Softmax and Cross-entropy for multi-class classification
- How to train a Deep MLP?
Convolutional Neural Network
- Biological inspiration: Visual Cortex
- Convolution: Edge Detection on images
- Convolution: Padding and strides
- Convolution over RGB images
- Convolutional layer
- Max-pooling
- CNN Training: Optimization
- Receptive Fields and Effective Receptive Fields
- ImageNet dataset
- Data Augmentation
- Convolution Layers in Keras
- AlexNet
- VGGNet
- Residual Network
- Inception Network
- What is Transfer learning
Recurrent Neural Network
- Why RNNs?
- Recurrent Neural Network
- Training RNNs: Backprop
- Types of RNNs
- Need for LSTM/GRU
- LSTM
- GRUs
- Deep RNN
- Bidirectional RNN