Machine Learning System Design
ML's value is evident in predictions for service, resource, and cost efficiency. This course sharpens ML system design, from problem framing to deployment, covering principles and hands-on challenges.
Limited time offer: $900 Off!
Prepare for ML System Design (in a post-GenAI era)
- 00 Days
- 00 Hours
- 00 Minutes
- 00 Seconds
Course Information
Contents |
About 35 hours of video lectures & 10 hours of assignment review |
Instructor |
Various FAANG+ instructors |
Dates |
June 7 - July 28, 2024 |
Online Sessions |
Every Sunday 8:30 am - 1:30 pm PST |
Online Assignment Review |
Every Wednesday 6:00 pm - 8:00 pm PST |
| Prerequisite | High-level understanding with machine learning process and techniques |
Machine learning significance continues to rise due to its powerful predictive abilities, revolutionizing areas such as customer service, resource allocation, and cost reduction. Recent advancements in large language models and deep learning techniques have further propelled this trend, promising even greater efficiency and effectiveness in various domains.
This course offers a transformative opportunity to boost your career in machine learning and gain more confidence in approaching ML system design interviews. By acquiring advanced skills in Machine Learning System Design, you'll position yourself as a competent candidate during the job interview process, and an expert who can tackle the ML design problems at scale and competitive edge required in big tech companies. Whether you're a seasoned professional or a newcomer, this program equips you with the tools and knowledge to excel in today's competitive job market.
The demand for machine learning professionals is on the rise, mastering system design can open doors to lucrative positions in tech companies, research institutions, and startups. Invest in your future and stay ahead of the curve with specialized expertise in machine learning system design.
The course includes:
-
Fundamentals review
-
A framework for approaching ML design problems
-
End-to-end design of key ML design problems
- Exploiting LLM and GenAI techniques to tackle more challenging ML problems, or optimize existing problems for performance, scalability, interpretability, and creativity.
Machine learning (ML) system design can greatly benefit from Large Language Models (LLMs) and Generative AI (GenAI) techniques. LLMs, such as transformer-based models, excel in understanding and generating natural language, enabling more nuanced text analysis, sentiment understanding, and context comprehension. This capability enhances various ML tasks, including language translation, sentiment analysis, and text summarization. On the other hand, GenAI techniques like generative adversarial networks (GANs) and variational autoencoders (VAEs) enable the generation of realistic and creative outputs, such as images, music, and text. By integrating LLM and GenAI techniques into ML system design, we can achieve improved performance, higher accuracy, and greater flexibility in addressing complex real-world challenges across diverse domains, from natural language processing to computer vision and creative AI applications.
Led by experienced instructors experienced in building scalable systems, sessions focus on fostering independent problem-solving, idea exchange, and constructive feedback. Participants can develop their skills to excel in a competitive environment.
Course Outline
-
-
Introducing Machine Learning System Design
-
-
-
Common issues in ML system design
-
Master template for ML System design
-
Framing a business problem using ML
-
Training Data Collection
-
Feature Engineering
-
Model Selection, development, and training
-
Model Evaluation
-
Deployment and Maintenance
-
-
-
Search Ranking
FREE PREVIEW -
Week 1: ML System Design - Workflow and Steps
-
Week 1: Search Engine
-
Week 2: Recommendation System
-
Week 2: Harmful Content Detection/Content moderation
-
Week 3: Ad Click prediction
-
Week 3: Fraud Detection
-
Week4: Text Summarization
-
Week 4: Question Answering
-
Week 5: Object Detection and Maps Image Blurring
-
Week 5: Text to Image
-
-
-
Week 1 - Ranking Specialization
-
Week 2: Recommendation Engines Specialization
-
Week 3: Advertising Specialization
-
Week 4: NLP Specialization
-
Week 5: Image Recognition and Generation Specialization
-
About this course
- $2,499.00
- 25 lessons
Reviews from previous batches
Very good course in ML System Design with good instructor
Chi Hoang
- This course teaches ML System Design (and NOT about basic ML) to solve actual problems such as: recommendation systems, ranking systems, searching systems, NLP problems, that you may see in real interviews. - Learners should have basic knowled...
Read More- This course teaches ML System Design (and NOT about basic ML) to solve actual problems such as: recommendation systems, ranking systems, searching systems, NLP problems, that you may see in real interviews. - Learners should have basic knowledge about ML to take full advantages of the course. - Overall this is a must-take course for learners aimed to tackle ML SD interviews in FAANG companies. The course will provide you with a general framework with 8 steps to handle almost any ML SD problems. Instructors are current FAANG software engineers, very knowledgeable and responsive in answering questions.
Read LessGreat aid in interview preparation!
Aum Rajadnye
I found the case studies covered in the ML System Design course to be not only very relevant to the current state of ML/DL but also covered in depth, especially the NLP use cases. Also, the mid-week practice sessions helped to reinforce what was t...
Read MoreI found the case studies covered in the ML System Design course to be not only very relevant to the current state of ML/DL but also covered in depth, especially the NLP use cases. Also, the mid-week practice sessions helped to reinforce what was taught on the Sunday class.
Read LessGreat Course for Software Engineers making the Transition to ML Engg. or ML Related roles
Roop G
I am a Full Stack Cloud Native Engineer(15+ years) making the transition, and I had completed Machine Learning Certificate and Deep Learning Certificate already. The course helped me answer the questions around ML in practice and Project Situati...
Read MoreI am a Full Stack Cloud Native Engineer(15+ years) making the transition, and I had completed Machine Learning Certificate and Deep Learning Certificate already. The course helped me answer the questions around ML in practice and Project Situations. The System Design Course elucidates the key steps in ML Projects and a Deep Dive on each of the Key Steps. Explaining and Rationalizing decisions/prospective-options at each step. The Instructors/specialists were loaded with both scientific and practical knowledge of ML Use Cases. All of them were Leading Key Projects in Focus ML areas at leading organizations at the cutting edge of ML(so kind of them to share the experience and knowhow). Silicon Insider mentor kept tab on the progress of the class in the session and steer the conversation so as to focus on what the students need at that juncture, I would Highly recommend this course for all Software Engineers in General irrespective of if they want to work as ML Engineers or not.
Read LessExcellent Course for ML System Design. Highly Recommend!
Alan Varghese
This course teaches how to use machine learning for various use cases. I find the course and the instructors collaborative. The instructors were knowledgeable in their field and could quickly and thoroughly address any questions. I would encourage...
Read MoreThis course teaches how to use machine learning for various use cases. I find the course and the instructors collaborative. The instructors were knowledgeable in their field and could quickly and thoroughly address any questions. I would encourage anyone who knows the basics of machine learning and the classical machine learning fundamentals to take this course to understand how the design of an ML system will work. As for me, this course allowed me to restart my ML learning after a long break.
Read LessDiscover your potential, starting today
Search Ranking Specialization
1) Learn how to design a search engine system leverage ML
2) Deep dive into core modeling approaches
3) Two-tower architecture for ranking and retreival.
4) Application of fast KNN
5) Feature engineering for search ranking
6) Offline and online metrics
We also look at recent advances of search through LLM and how such a system can benefit from improved query understanding, context-aware models, query-specific ranking models and multimodal interfaces.
Recommender Systems Specialization
We cover different aspects in designing recommender systems, including 1) Classic and modern approaches to recommendation 2) Cold-start problem and other challenges 3) Data Sparsity and dense representation 4) Scalability issues 5) Dynamic user preferences and real-time recommendation 6) user and item representations.
We also delve into application of GenAI and LLM in recommender systems, such as improved understanding of user intent and content semantics, enhanced personalization and contextual recommendations, continuous learning and adaptation, and enhanced multimodal recommendation.
Natural Language Processing Specialization
The main focus is to understand how to design text summarization and question answering, two popular system design problems, delvomg deep into the challenges involved in designing these complex systems. We also discuss how how large language models (LLMs) and advancements in Generative AI (GenAI) techniques are revolutionizing the design of these systems, through comprehending and condensing large volumes of text into concise summaries, preserving essential information while discarding redundancies.
Image Understanding and Generation Specialization
We focus on intricate challenges of designing systems which require deep understanding of images, such as object detection and text-to-image conversion systems. In addition to end-to-end design, we discuss how LLMs can facilitate more nuanced understanding of textual descriptions. GenAI models, such as generative adversarial networks (GANs), can be employed to synthesize high-quality images based on textual input, pushing the boundaries of creative AI. Learners gain valuable insights into the intersection of language understanding and visual perception in machine learning system design.
Ad Click Prediction specialization
Ad click prediction is crucial for forecasting user engagement with ads based on contextual factors and behavior signals. We take a deep dive into the problem of ad click prediction, and practical considerations of designing an end-to-end system with focus on ML workflow steps. We also look into how LLMs and GenAI techniques can enhance ad click prediction by improving natural language interpretation and leveraging generative models and reinforcement learning for ad targeting and personalization.
