Share
Explore
Building the AI Model : Test Questions Bank
Blog Articles:
Suppose you don’t want to serve your model on Hugging Face Spaces.
What would you need to do to be able to host your own AI Models there?
w25 MARCH 17
Explain the key differences between the initial deterministic chat bot and the final AI model that uses machine learning. How does the AI model's approach to generating responses differ?
The initial deterministic chat bot relied on simple text matching and pre-written responses, while the final AI model uses machine learning to classify user inputs and generate responses based on probabilities. The AI model learns patterns in the training data and can make predictions on new inputs, rather than just repeating pre-programmed responses.
Describe the process of vectorization and how it allows the AI model to understand and learn from text data.
What are the benefits of this approach compared to simple pattern matching?
Vectorization converts words into numerical values that the AI model can process and learn from. This allows the model to understand relationships between words and generalize beyond just matching specific phrases. Compared to simple pattern matching, vectorization enables the model to learn more abstract concepts and respond appropriately to a wider range of inputs.
Discuss the importance of persistent learning in the final chat bot implementation.
How does this allow the model to continue improving over multiple sessions, and what are the technical considerations around implementing this functionality?
Persistent learning allows the chat bot to retain and build upon knowledge gained from previous interactions, rather than starting from scratch each time. This enables the model to continuously improve its understanding and responses. Technically, this is implemented by saving the model's state to a file, which is then loaded at the start of each new session. The instructor notes that there are considerations around where and how this file is stored to ensure data persistence across different environments.
w25 ; January 27 Session 4
A review of our January 20 class:
Software Model Architecture
Intersection with consumer demand and what people will pay for
Summary
Discussion question that covers the key topics discussed in the lecture:
What are the key considerations and challenges in developing appropriate software engineering methodologies and processes for building AI models, particularly in the context of generative language models? How does the unified model engineering process differ from traditional software development approaches, and what are the benefits and drawbacks of this new methodology?
The key topics covered include:
The importance of safety guidelines and guard rails for AI models
The need for a specialized software development methodology for AI, rather than adapting traditional approaches
The role of foundational models, embeddings, and Bayesian training in building generative language models
The practical considerations of deploying AI models on platforms like Hugging Face
The philosophical and historical context of AI model development
This question encourages students to think critically about the unique challenges of AI development and how new methodologies like the unified model engineering process can address them, while also considering the tradeoffs and practical implementation details
Discussion question related to social and safety trust issues in AI development:
What are the key ethical and safety considerations that need to be addressed when developing and deploying generative AI language models for public-facing applications? How can AI developers build in appropriate safeguards and guard rails to ensure these models are used responsibly and do not cause harm?
Some key points to consider:
The potential for AI models to generate content that promotes violence, hate, or other harmful narratives, and how to prevent this.
The challenge of defining appropriate boundaries and limitations for AI assistants to avoid giving advice on sensitive topics like investments or medical issues.
The need to be transparent about the capabilities and limitations of AI models to manage user expectations and build trust.
Strategies for monitoring AI model outputs and having human oversight to quickly identify and address problematic content.
The role of regulatory frameworks and industry standards in establishing safety guidelines for public-facing AI applications.
This question encourages students to think deeply about the social implications of their work and how to proactively address ethical concerns around the deployment of powerful language models. Developing responsible AI practices should be a core consideration in the unified model engineering process.
What are the key considerations and challenges in developing appropriate software engineering methodologies and processes for building AI models, particularly in the context of generative language models?
How does the unified model engineering process differ from traditional software development approaches, and what are the benefits and drawbacks of this new methodology?
The key considerations and challenges in developing appropriate software engineering methodologies for building AI models, particularly generative language models, include:
The key difference between the unified model engineering process and traditional software development is the emphasis on the unique challenges of AI. Rather than trying to fit AI into existing methodologies, the unified process is designed from the ground up to address the unpredictability, domain-specificity, and continuous learning needs of AI systems.
The benefits of this approach include greater adaptability, stronger safeguards, and more effective collaboration between technical and domain experts. However, the drawbacks may include a steeper learning curve for teams unfamiliar with AI-specific processes, as well as the need for more specialized skills and tools.
Overall, the unified model engineering process represents an important evolution in software development to meet the unique demands of building robust and trustworthy AI applications, particularly in high-stakes domains like generative language models.
Discussion question related to the architecture and operation of an AI model:
How do the core concepts of tokenization, embeddings, and neural network training work together to enable the generation of coherent and contextually-appropriate language by an AI model? What are the key architectural considerations and design choices that impact the performance and capabilities of a generative language model?
Some key points to explore:
The role of tokenization in breaking down input text into discrete units that can be processed by the model
How embeddings represent these tokens as numerical vectors that capture semantic relationships
The function of neural network architectures like transformers in learning patterns and generating new text
The importance of the training dataset and Bayesian training techniques in shaping the model's knowledge and response generation
Factors like model size, depth, attention mechanisms, and other architectural choices that influence the model's fluency, coherence, and ability to understand context
This question dives into the technical underpinnings of how generative language models operate, encouraging students to think critically about the interplay of different components and how design decisions impact the model's performance. Understanding these architectural principles is crucial for building effective AI systems.
What specific steps can students take during this course and beyond to make themselves competitive candidates for entry-level AI development roles?
How can they leverage the skills and experience gained here to stand out in the job market?
During this course, students can take several key steps to make themselves competitive candidates for AI development jobs:
Beyond the course, students can further strengthen their candidacy by:
By leveraging the hands-on experience, tool proficiency, and broader understanding of AI gained in this course, students can position themselves as attractive candidates for entry-level AI development roles. Demonstrating a combination of practical skills, industry awareness, and a proactive approach to professional development will help them stand out in the job market.
w25 : January 20 Session 3
Summarized Review Questions and Detailed Answers
Question 1:
What are the key differences between object-oriented programming and probabilistic programming, and how do these differences impact the design and development of AI models?
Summary of the Question:
This question asks students to compare two programming paradigms—object-oriented programming (OOP) and probabilistic programming (PP)—and explain how their differences influence the way AI models are designed and developed. It also touches on the statistical and mathematical foundations of AI, the challenges of working with different types of data, and the practical considerations for deploying AI models.
Detailed Answer:
Question 2:
How do the concepts of tokens, weightings, and embeddings relate to the architecture and performance of AI language models? Explain the importance of these concepts and how they impact the training and deployment of AI applications.
Summary of the Question:
This question focuses on the fundamental building blocks of AI language models—tokens, weightings, and embeddings—and their role in model architecture and performance. It also asks students to explain how these concepts influence the training and deployment of AI applications.
Detailed Answer:
Question 3 (New Question with "First Day on the Job" Flavor):
Imagine you are tasked with building a chatbot for a customer service application. How would you use the concepts of tokenization, embeddings, and neural networks to design and train the chatbot? What challenges might you face, and how would you address them?
Summary of the Question:
This question asks students to apply their understanding of tokenization, embeddings, and neural networks to a practical task: building a chatbot. It also encourages them to think about potential challenges and solutions.
Detailed Answer:
This question encourages students to think critically about the practical application of AI concepts in a real-world scenario.
August 2
Table 1
Question
Correct Answer
Answer 1
Answer 2
Answer 3
Answer 4
Column 7
Explanation
Explanation 2
In the conceptual model for AI language models, which layer receives raw text?
1
Input Layer
Embedding Layer
Encoder Layer
Output Layer
Output Layer
The Input Layer is responsible for receiving raw text in the conceptual model.
The Input Layer is responsible for receiving raw text in the conceptual model.
What does the Embedding Layer do in an AI language model?
2
Generate output text
Convert words to numerical vectors
Extract patterns
Produce final text prediction
Produce final text prediction
The Embedding Layer converts words to numerical vectors, allowing the model to process text mathematically.
The Embedding Layer converts words to numerical vectors, allowing the model to process text mathematically.
Which layers are responsible for extracting patterns and relationships in the text?
3
Input Layers
Embedding Layers
Encoder Layers
Output Layers
Output Layers
Encoder Layers are responsible for extracting patterns and relationships from the input text.
Encoder Layers are responsible for extracting patterns and relationships from the input text.
In the provided code example, what type of neural network layer is used for the encoder and decoder?
3
Dense
Embedding
LSTM
Convolutional
Convolutional
The code example uses LSTM (Long Short-Term Memory) layers for both the encoder and decoder.
The code example uses LSTM (Long Short-Term Memory) layers for both the encoder and decoder.
What is the purpose of the output layer in the LanguageModel class?
4
Receive input
Generate embeddings
Process sequences
Produce final text prediction
Produce final text prediction
The output layer (Dense layer) in the LanguageModel class produces the final text prediction.
The output layer (Dense layer) in the LanguageModel class produces the final text prediction.
How is modular design in AI language models similar to Java programming?
1
Each layer is a self-contained unit
Layers are written in Java
Models use Java Virtual Machine
AI models are objects
AI models are objects
Modular design in AI models is similar to Java as each layer is a self-contained unit with a specific purpose, like Java objects.
Modular design in AI models is similar to Java as each layer is a self-contained unit with a specific purpose, like Java objects.
How does data flow in an AI language model compare to Java object interactions?
3
Through SQL queries
Via HTTP requests
Through the layers, similar to method calls
Using global variables
Using global variables
Data flows through the layers in AI models, similar to method calls between Java objects.
Data flows through the layers in AI models, similar to method calls between Java objects.
What concept in AI models is analogous to shared fields in Java objects?
1
The model's weights
The input data
The output predictions
The layer names
The layer names
The model's weights are like shared fields in Java objects, updated during training.
The model's weights are like shared fields in Java objects, updated during training.
How is the concept of composition applied in AI language models?
1
Layers are composed together to form the complete model
Models are composed of Java classes
Composition is not used in AI models
Models are composed of SQL tables
Models are composed of SQL tables
Layers are composed together to form the complete model, analogous to object composition in Java.
Layers are composed together to form the complete model, analogous to object composition in Java.
What OOP concept is similar to how the high-level AI model hides complex internal operations?
3
Inheritance
Polymorphism
Encapsulation
Overloading
Overloading
The high-level model hiding complex internal operations is similar to encapsulation in OOP.
The high-level model hiding complex internal operations is similar to encapsulation in OOP.
In the code example, what does the 'embedding_dim' parameter represent?
3
The size of the input vocabulary
The number of encoder layers
The dimension of word embeddings
The batch size for training
The batch size for training
The 'embedding_dim' parameter represents the dimension of word embeddings, determining how words are represented numerically.
The 'embedding_dim' parameter represents the dimension of word embeddings, determining how words are represented numerically.
What is the purpose of the 'vocab_size' parameter in the LanguageModel class?
2
To set the number of layers
To determine the size of the input vocabulary
To set the embedding dimension
To set the batch size
To set the batch size
The 'vocab_size' parameter determines the size of the input vocabulary, affecting the input and output layer sizes.
The 'vocab_size' parameter determines the size of the input vocabulary, affecting the input and output layer sizes.
Which method in the LanguageModel class is responsible for the forward pass of data?
2
init
call
fit
predict
The 'call' method in the LanguageModel class is responsible for the forward pass of data through the model.
The 'call' method in the LanguageModel class is responsible for the forward pass of data through the model.
What type of layer is used for the final output in the LanguageModel class?
3
LSTM
Embedding
Dense
Flatten
A Dense layer is used for the final output in the LanguageModel class.
A Dense layer is used for the final output in the LanguageModel class.
How many encoder layers are created in the example LanguageModel initialization?
3
1
2
3
4
The example initializes the LanguageModel with 3 encoder layers (num_layers = 3).
The example initializes the LanguageModel with 3 encoder layers (num_layers = 3).
What is the purpose of the 'return_sequences=True' parameter in the encoder LSTM layers?
3
To return the model to initial state
To allow sequences to be input
To output sequences for the next layer
To reverse the input sequence
To reverse the input sequence
The 'return_sequences=True' parameter allows the LSTM layer to output sequences for the next layer, maintaining temporal information.
The 'return_sequences=True' parameter allows the LSTM layer to output sequences for the next layer, maintaining temporal information.
Which TensorFlow module is primarily used in the code example?
2
tf.keras
tf.train
tf.estimator
tf.estimator
The code example primarily uses the tf.keras module for building the neural network model.
The code example primarily uses the tf.keras module for building the neural network model.
What would be a suitable method name for preprocessing input text in the LanguageModel class?
3
process_input
encode_text
preprocess_text
tokenize_input
tokenize_input
A suitable method name for preprocessing input text would be 'preprocess_text', clearly indicating its purpose.
A suitable method name for preprocessing input text would be 'preprocess_text', clearly indicating its purpose.
In the exercise, what functionality is suggested to be added to the LanguageModel class?
3
A method to visualize the model
A method to save the model
A method to generate text given a starting prompt
A method to evaluate the model's performance
A method to evaluate the model's performance
The exercise suggests adding a method to generate text given a starting prompt to the LanguageModel class.
The exercise suggests adding a method to generate text given a starting prompt to the LanguageModel class.
How does the conceptual model of AI language models help in understanding the architecture?
1
It provides a visual metaphor similar to Java objects
It explains the mathematical formulas used
It shows the exact TensorFlow implementation
It provides the training data required
It provides the training data required
The conceptual model helps understand AI language model architecture by providing a visual metaphor similar to Java objects, making it easier to grasp for those familiar with OOP concepts.
The conceptual model helps understand AI language model architecture by providing a visual metaphor similar to Java objects, making it easier to grasp for those familiar with OOP concepts.
There are no rows in this table
JULY 30:
Describe the key components of the AI application development methodology that we covered in this class, including the use of tools like Trello, Overleaf, and synthetic personalities created with AI assistants. Explain how these elements work together to support the successful delivery of the class project.
The Development of an AI application involves several stages; the mentioned tools help to facilitate the process in every stage. For instance, for project planning:
- A Trello board helps us to manage the project. We can create a list of tasks such as "To do," "In Progress," and "Done."
- Overleaf: This tool helps us create project documentation collaboratively, such as architecture design, research papers, model selection rationale, etc.
- Synthetic personalities: Can help in the data collection, such as synthetic data generation
Train your thinking to lean into / work with the AI agents and personalities you will build to amplify your cognitive scope and bankwidth. In addition to just to answering questions: Ask your AI to advise you on concerns which you SHOULD be thinking about which you have not get thought about.
Exam Question: How does your AI KNOW what you need that you have not yet considered?
Discuss the importance of the video component in the class project, as emphasized by Peter Sigurdson. Explain how creating and presenting a video can help reinforce learning and develop valuable skills for future job interviews and presentations.
You build a short look reward cycle of speaking and presenting knowledgably about these topics and getting a dopamine rush of confidence and encourage which spills over into your other arena.
Provide a comprehensive overview of the process for building the AI application that you are required to develop for the AML 3304 class, as described in our lectures.
Include the following key elements:
The software development methodology and tools used, such as the Unified Model Engineering Process, Trello for project management, and Overleaf for the LaTeX presentation document.
Video / read my materials on Unified Process:
The steps involved in constructing the AI model, including the use of Google Colab notebooks, PyTorch, TensorFlow, and potentially deploying the model to platforms like Hugging Face Spaces.
The importance of incorporating theoretical concepts and research questions into the project report to demonstrate an understanding of the underlying principles of AI and language models.
The role of synthetic personalities created using tools like Claude AI to assist in the development and delivery of the project, including providing guidance and feedback to the students.
Mid Term Review Test Prep:
What are the differences between old-school methodologies like Waterfall and Agile compared with Unified Process software development processes? Discuss this in the context of the Software Crisis of the 1970s.
Modern software development methodologies put the User at the Center by gather user stories which is what Unified process does.
Modern software development methodologies are “agile” meaning, we update the plan continually as we acquire new knowledge:
<What kind of knowledge?>
Knowledge of how the Business Domain operates
Knowledge of how our development technology stack tools work: programming languages, database.
What are you giving to OPEN AI in exchange for “free” access?
Training Data.
The analysts say that the big problem with the emerging Chat GPT 5 is: There is not enough data in the world to train next Gen AI?
Synthetic Data: Perry the Stochastic Parrot
The problem with Synthetic Data? “The 2 Irish men problem”
July 12 Attendance Quiz Start of class : AI/ML engineering practices
Want to print your doc?
This is not the way.
This is not the way.
Try clicking the ⋯ next to your doc name or using a keyboard shortcut (
CtrlP
) instead.