Home » Practical Deep Learning and Open AI Tools

Practical Deep Learning and Open AI Tools

הסמינר מלא

(לפרטים, ניתן לפנות לסופי sofil@johnbryce.co.il)

Main Speaker

Leonid Pevzner

Guest Speaker

מרצה אורח

Or Ben David

Learning Tracks

AI, Data

Course ID

42562

Date

01/12/2024

Time

Daily seminar
9:00-16:30

Location

John Bryce ECO Tower, Homa Umigdal 29 Tel-Aviv

Overview

This seminar is tailored to demonstrate the practical applications of deep learning with TensorFlow and the innovative capabilities of OpenAI tools. Participants will engage in hands-on sessions to learn how to apply Convolutional Neural Networks (CNN) to the Fashion MNIST dataset, use Autoencoders for noise reduction in images, and forecast weather using Long Short-Term Memory (LSTM) networks. Additionally, the seminar will delve into the utilization of OpenAI models, focusing on different model selections based on task requirements, leveraging embeddings for enhanced model performance, and mastering prompt engineering for optimal model interactions. Designed for developers and researchers interested in deep learning and AI, this seminar provides a comprehensive overview of creating impactful solutions using TensorFlow and OpenAI’s cutting-edge technologies, ensuring attendees leave with a solid foundation in both theory and practical application.

Who Should Attend

Prerequisites

Python development
Familiarity with basic ML concepts

Course Contents

Introduction to Deep Learning and TensorFlow
- Overview of deep learning concepts and applications
- Introduction to TensorFlow: features, ecosystem, and advantages
- Setting up the TensorFlow environment

Hands-on: CNN with Fashion MNIST
- Understanding Convolutional Neural Networks (CNN)
- Loading and preprocessing the Fashion MNIST dataset
- Building, training, and evaluating a CNN model with TensorFlow
- Best practices for image classification tasks

Hands-on: Autoencoder for Noise Reduction in MNIST
- Introduction to Autoencoders and their applications
- Discussing the concept of noise reduction in images
- Building an Autoencoder with TensorFlow to clean noisy MNIST images
- Evaluating the performance and visualizing the results

Hands-on: Weather Forecasting with LSTM
- Understanding Long Short-Term Memory (LSTM) networks
- Discussing time series forecasting and its challenges
- Implementing an LSTM model for weather forecasting
- Data preparation and model tuning for time series data

Introduction to OpenAI and GPT Models
- Overview of OpenAI and its contributions to AI research
- Exploring GPT models: capabilities, limitations, and use cases
- Guidelines for accessing and using OpenAI models responsibly

Practical Applications of OpenAI Models
- Demonstrating various applications of GPT models: content creation, question-answering, code generation, etc.
- When to use different OpenAI models based on task complexity and requirements
- Introduction to embeddings from OpenAI: extracting features, semantic search, and more

Mastering Prompt Engineering
- The art and science of prompt engineering: crafting effective prompts to guide model responses
- Strategies for iterative prompt refinement for better outcomes
- Tips and best practices for advanced prompt engineering