Image 1

Mocksphere for Students

Image 2

Mocksphere for Teacher

Image 5

Mocksphere for Parents/Guardians

Image 3

Mocksphere for Job Seeker

Image 4

Mocksphere for Recruiter

Online Workshop
Online Workshop Every Week

Join our free weekly interactive learning sessions.

Master AI/ML with instant feedback and personalized learning

"Cogito, ergo sum" (I think, therefore I am)

— René Descartes

René Descartes
Accenture
Activision
Adobe
Airbnb
Airtable
Alteryx
Amazon
Amd
Anthropic
Apple
Atlassian
Bank Of America
Binance
Bitbucket
Blizzard
Box
Broadcom
Bytedance
Canonical
Canva
Circle
Cisco
Coinbase
Company
Crowdstrike
Databricks
Datadog
Deepmind
Dell
Discord
Docker
Doordash
Dropbox
Ea
Ebay
Elastic
Electronic Arts
Epic Games
Etsy
Expedia
Facebook
Figma
Flipkart
Github
Gitlab
Goldman Sachs
Google
Grubhub
Hashicorp
Hello Interview
Accenture
Activision
Adobe
Airbnb
Airtable
Alteryx
Amazon
Amd
Anthropic
Apple
Atlassian
Bank Of America
Binance
Bitbucket
Blizzard
Box
Broadcom
Bytedance
Canonical
Canva
Circle
Cisco
Coinbase
Company
Crowdstrike
Databricks
Datadog
Deepmind
Dell
Discord
Docker
Doordash
Dropbox
Ea
Ebay
Elastic
Electronic Arts
Epic Games
Etsy
Expedia
Facebook
Figma
Flipkart
Github
Gitlab
Goldman Sachs
Google
Grubhub
Hashicorp
Hello Interview
Free Problems
View All Free Problems
Understanding Reasoning vs Generic LLMs
This problem set explores the key differences between reasoning and generic large language models (LLMs) based on the video "What is the difference between Reasoning and Generic LLMs?". The problems cover fundamental concepts, practical applications, and analytical comparisons between these two types of AI models.
12 pts Easy 104 reasoning-questions llm-types basic-concepts +7
Chain of Thought Reasoning Fundamentals
This problem set covers the key concepts from Lecture 2 on Chain of Thought Reasoning, including inference time compute scaling, few-shot prompting, zero-shot reasoning, and the emergent reasoning abilities in large language models. The problems progress from basic concepts to advanced analytical questions based on the video content.
34 pts Medium 101 inference-time-compute reasoning-llms computational-resources +7
Chapter 8 Achieving Higher Throughput and Lower Latency (DMLP)
This problem set covers key techniques for improving system efficiency in model-parallel training and inference from Chapter 8. You'll explore layer freezing, memory optimization, model decomposition, distillation, and bit reduction strategies to achieve higher throughput and lower latency in distributed machine learning systems.
26 pts Medium 101 layer-freezing model-parallelism optimization +7
Chapter 12 Advanced Techniques for Further Speed-Ups (DMLP)
This problem set covers advanced techniques for optimizing distributed deep neural network training and serving, including performance debugging with NVIDIA Nsight, job migration and multiplexing, and heterogeneous model training. These techniques build upon the distributed training methodologies discussed in previous chapters to achieve further speed-ups and improved hardware utilization.
21 pts Medium 96 performance-profiling nvidia-nsight gpu-communication +7
Chapter 11 Elastic Model Training and Serving (DMLP)
This problem set covers key concepts from Chapter 11: Elastic Model Training and Serving, focusing on adaptive resource allocation for distributed machine learning workloads. The problems test understanding of elastic training in both data and model parallelism, implementation using adaptdl, and elastic model serving concepts.
21 pts Medium 96 adaptive-training data-parallelism resource-allocation +7
Chapter 6 Pipeline Input and Layer Split (DMLP)
This problem set covers key concepts from Chapter 6 on improving system efficiency in model parallelism training. You'll explore pipeline parallelism, intra-layer splitting, GPU utilization analysis, and the trade-offs between different model parallelism approaches. These problems test your understanding of how to optimize distributed machine learning systems for large NLP models.
24 pts Medium 104 gpu-utilization model-parallelism efficiency-analysis +7
Premium Problems
View All Premium Problems
Chapter 4 Fundamental transformation and decomposition of matrices (LAMCM)
This problem set covers fundamental matrix transformations and decompositions including similarity transforms, orthogonal matrices, elementary row operations, triangular decomposition, Cholesky factorization, Jordan canonical forms, singular value decomposition, and Givens/Householder transforms. These concepts are essential for understanding matrix analysis and numerical linear algebra.
30 pts Medium 103 similarity-transform matrix-properties linear-algebra +7
Python I/O and Data Pipeline Assessment - Part 4
20 questions focused on PyTorch Dataset/DataLoader design: map/iterable datasets, transforms, custom collate/padding, worker seeding/sharding, num_workers/pin_memory/prefetch_factor, caching, memmap/shared memory, batching by size, profiling, and performance tuning.
10.00 60 pts Medium 98 torch.utils.data.dataset pytorch dataset +7
Chapter 2 Numeric Python (NPSCDS)
This problem set covers key concepts from Chapter 2: Vectors, Matrices, and Multidimensional Arrays. The problems test understanding of NumPy array fundamentals, including array creation, indexing, slicing, operations, and vectorized computing. Each question is designed to reinforce the core concepts presented in the chapter.
5.00 26 pts Medium 99 numpy-arrays array-attributes shape +7
USAAIO 2025 R1P3 - Logistic Regression Implementation
This problem focuses on implementing logistic regression from scratch using the Titanic dataset. You will work through data pre-processing, mathematical derivations, and implement both gradient descent and Newton's method for logistic regression. The dataset contains passenger information from the Titanic, and your goal is to predict survival based on various features.
10.00 48 pts Easy 93 data-loading pandas data-exploration +7
USAAIO 2025 R1P2 - Basics of Neural Network - From Linear Regression to DNN Training
This problem is about the basics of neural network. Each part has its particular purpose to intentionally test you something. Do not attempt to find a shortcut to circumvent the rule. And all coding tasks shall run on CPUs, **not GPUs**.
10.00 36 pts Easy 96 learning-rate-scheduler pytorch optimization +12
USAAIO 2025 R1P1 - Fibonacci Matrix Form
Let us consider the following sequence: $$ F_n = F_{n-1} + F_{n-2},\ \forall\ n \ge 2. $$
8.00 27 pts Medium 96 fibonacci sequence linear algebra matrix form +7

Knowledge Graphs

USA AI Olympiad

Explore competitive programming and AI contest preparation concepts

View Full Graph
Grade 5 Math

Discover elementary mathematics concepts and learning paths

View Full Graph

Featured Docs

View All PDFs
Cover of System Design Interview: An Insider's Guide Volume 2
System Design Interview: An Insider's Guide Volume 2
116 questions 348 pts
Cover of System Design Interview: An Insider's Guide
System Design Interview: An Insider's Guide
108 questions 317 pts
Cover of UNICALLI: A UNIFIED DIFFUSION FRAMEWORK FOR COLUMN-LEVEL GENERATION AND RECOGNITION OF CHINESE CALLIGRAPHY
UNICALLI: A UNIFIED DIFFUSION FRAMEWORK FOR COLUMN-LEVEL GENERATION AND RECOGNITION OF CHINESE CALLIGRAPHY
10 questions 38 pts
Cover of The Principles of Deep Learning Theory
The Principles of Deep Learning Theory
107 questions 418 pts

Featured Books

View All Books
Cover of Acing the System Design Interview
Acing the System Design Interview
153 questions 456 pts
Cover of Numerical Python: Scientific Computing and Data Science Applications with Numpy, SciPy and Matplotlib
Numerical Python: Scientific Computing and Data Science Applications with Numpy, SciPy and Matplotlib
240 questions 684 pts
Cover of Hands-On Machine Learning with Scikit-Learn and PyTorch
Hands-On Machine Learning with Scikit-Learn and PyTorch
200 questions 554 pts
Cover of Deep Reinforcement Learning Hands-On - Third Edition
Deep Reinforcement Learning Hands-On - Third Edition
222 questions 720 pts

Featured Videos

View All Videos
Cover of Flow-Matching vs Diffusion Models explained side by side
Flow-Matching vs Diffusion Models explained side by side
10 questions 29 pts
Cover of Attention in transformers, step-by-step | Deep Learning Chapter 6
Attention in transformers, step-by-step | Deep Learning Chapter 6
10 questions 30 pts
Cover of Knowledge Distillation: How LLMs train each other
Knowledge Distillation: How LLMs train each other
10 questions 27 pts
Cover of Diffusion Model
Diffusion Model
10 questions 32 pts

Popular Topics

beginner 459 easy 217 fundamental-concepts 112 optimization 100 performance 87 distributed-systems 85 medium 85 machine-learning 84 fundamentals 83 basic-concepts 80 linear-algebra 78 architecture 77 classification 73 data-structures 73 system-design 66 time-complexity 66 scalability 65 calculation 63 neural-networks 62 machine learning 61
Click on any tag to filter problems by that topic