Deep Learning: From Perceptron to Large Language Models (training)

Colleagues, the Deep Learning: From Perceptron to Large Language Models training program will introduce you to the essential building blocks of deep neural networks, such as artificial neurons and fully connected, convolutional, and recurrent layers. It describes how these concepts are used to build modern networks for computer vision and natural language processing (NLP), including large language models and multimodal networks. Skill-based training modules address: 1) Deep Learning Introduction - Deep Learning and Its History, Prerequisites, 2) Neural Network Fundamentals - The Perceptron and Its Learning Algorithm, Programming Example: Perceptron, Understanding the Bias Term, Matrix and Vector Notation for Neural Networks, Perceptron Limitations, Solving Learning Problem with Gradient Descent,  Computing Gradient with the Chain Rule, The Backpropagation Algorithm, Programming Example: Learning the XOR Function, What Activation Function to Use, 3) Neural Network Fundamentals II - Datasets and Generalization, Multiclass Classification, Programming Example: Digit Classification with Python, DL Frameworks, Programming Example: Digit Classification with TensorFlow, Programming Example: Digit Classification with PyTorch, Avoiding Saturated Neurons and Vanishing Gradients - Part I, Avoiding Saturated Neurons and Vanishing Gradients - Part II, Variations on Gradient Descent, Programming Example: Improved Digit Classification with TensorFlow, Programming Example: Improved Digit Classification with PyTorch, Problem Types, Output Units, and Loss Functions, Regularization Techniques, Programming Example: Regression Problem with TensorFlow, Programming Example: Regression Problem with PyTorch, 4) Convolutional Neural Networks (CNN) and Image Classification - The CIFAR-10 Dataset, Convolutional Layer, Building a Convolutional Neural Network, Programming Example: Image Classification Using CNN with TensorFlow & PyTorch, AlexNet, VGGNet, GoogLeNet, ResNet, Amplifying Your Data, Efficient CNNs, 5) Recurrent Neural Networks (RNN) and Time Series Prediction - Problem Types Involving Sequential Data, Recurrent Neural Networks, Programming Example: Forecasting Book Sales with TensorFlow & PyTorch, Backpropagation Through Time and Keeping Gradients Healthy, Long Short-Term Memory, Autoregression and Beam Search, Programming Example: Text Autocompletion with TensorFlow & PyTorch, 6) Neural Language Models and Word Embeddings - Language Models, Word Embeddings, Programming Example: Language Model and Word Embeddings with TensorFlow & PyTorch, Word2vec, Programming Example: Using Pre Trained GloVe Embeddings, Handling Out-of-Vocabulary Words with Wordpieces, 7) Encoder-Decoder Networks, Attention, Transformers, and Neural Machine Translation - EncoderDecoder Network for Neural Machine Translation, Programming Example: Neural Machine Translation with TensorFlow & PyTorch, Attention, The Transformer, 8) Large Language Models - Overview of BERT & GPT, From GPT to GPT4, Handling Chat History, Prompt Tuning, Retrieving Data and Using Tools, Open Datasets and Models, Demo: Large Language Model Prompting, 9) Multimodal Networks and Image Captioning - Multimodal learning, Programming Example: Multimodal Classification with TensorFlow & PyTorch, Programming Example: Multimodal Classification with PyTorch, Image Captioning with Attention, Programming Example: Image Captioning with TensorFlow & PyTorch, , Multimodal Large Language Models, 10) Multi-Task Learning and Computer Vision Beyond Classification - Multitask Learning, Programming Example: Multitask Learning with TensorFlow & PyTorch, Programming Example: Multitask Learning with PyTorch, Object Detection with R-CNN, Improved Object Detection with Fast and Faster R-CNN, Segmentation with Deconvolution Network and U-Net, Instance Segmentation with Mask R-CNN, and 11) Applying Deep Learning - Ethical AI and Data Ethics, Process for Tuning a Network. 

Enroll today (teams & executives are welcome): https://tinyurl.com/yckrv8xj 

Download your free AI-ML-DL - Career Transformation Guide.

For your listening-reading pleasure:

1 - “AI Software Engineer: ChatGPT, Bard & Beyond” (Audible) or (Kindle)  

2 - “ChatGPT - The Era of Generative Conversational AI Has Begun” (Audible) or (Kindle) 

3 - “ChatGPT, Gemini and Llama - The Journey from AI to AGI, ASI and Singularity” (Kindle) or (Audible - coming soon!)

Much career success, Lawrence E. Wilson - AI Academy (share with your team)