The
IBM AI Engineering Professional Certificate on Coursera is a 13-course programme that takes you from machine learning with Python through deep learning in Keras, TensorFlow and PyTorch to generative AI, fine-tuning transformers, RAG and LangChain. Every course has graded module quizzes and a final exam. The 102+ solved MCQs below follow the certificate course by course, with the correct option marked and a short explanation under every question, so you can revise before each graded quiz. New to AI? Start with
IBM AI Fundamentals first. A
free PDF of the full set is at the end of the page.
ย
๐
Course 1 โ Machine Learning with Python (Questions 1โ22)
Regression, classification, KNN, decision trees, SVM, clustering and evaluation with scikit-learn
Question 01
In machine learning, what is the difference between supervised and unsupervised learning?
ASupervised uses labelled data; unsupervised finds patterns in unlabelled data โ
BSupervised is faster
CUnsupervised needs more labels
DThere is no difference
๐ก ExplanationSupervised models learn a mapping from inputs to known outputs; unsupervised models discover structure such as clusters.
Question 02
Which of the following is a regression problem?
APredicting whether an email is spam
BPredicting the CO2 emission of a car from its engine size โ
CGrouping customers into segments
DDetecting objects in an image
๐ก ExplanationRegression predicts a continuous value; the course uses the CO2 emissions dataset for this.
Question 03
Which of the following is a classification problem?
APredicting house prices
BPredicting whether a tumour is benign or malignant โ
CForecasting temperature
DEstimating salary
๐ก ExplanationClassification predicts a discrete category.
Question 04
In simple linear regression, the model fits:
AA curve through all points
BA straight line that minimises the sum of squared errors โ
CA decision boundary
DClusters
๐ก ExplanationOrdinary least squares finds the line with the lowest mean squared error.
Question 05
Which metric is commonly used to evaluate a regression model?
AAccuracy
BMean Squared Error (MSE) โ
CF1 score
DJaccard index
๐ก ExplanationMSE, RMSE, MAE and R-squared are regression metrics.
Question 06
What does R-squared measure?
AClassification accuracy
BThe proportion of variance in the target explained by the model โ
CThe number of features
DThe learning rate
๐ก ExplanationR-squared of 1 means a perfect fit; 0 means no better than the mean.
Question 07
What is the purpose of splitting data into training and test sets?
ATo make the dataset smaller
BTo estimate how the model performs on unseen data โ
CTo speed up training
DTo remove outliers
๐ก ExplanationOut-of-sample evaluation shows how well the model generalises.
Question 08
Which algorithm classifies a point based on the majority class of its nearest neighbours?
ALogistic regression
BK-Nearest Neighbours (KNN) โ
CK-means
DLinear regression
๐ก ExplanationKNN is a lazy, instance-based classifier.
Question 09
In KNN, what happens if K is too small?
AThe model underfits
BThe model becomes sensitive to noise and overfits โ
CTraining takes longer
DAccuracy always improves
๐ก ExplanationA small K captures noise; a very large K over-smooths.
Question 10
A decision tree chooses the attribute to split on by:
ARandom selection
BMaximising information gain (reducing entropy) โ
CAlphabetical order
DMinimising the number of nodes
๐ก ExplanationEntropy measures impurity; the best split lowers it most.
Question 11
Logistic regression is used for:
APredicting continuous values
BBinary classification, outputting a probability โ
CClustering
DDimensionality reduction
๐ก ExplanationIt applies the sigmoid function to a linear combination of features.
Question 12
The sigmoid function outputs values between:
A-1 and 1
B0 and 1 โ
C0 and infinity
D-infinity and infinity
๐ก ExplanationThe output can be read as a probability.
Question 13
What does a Support Vector Machine (SVM) try to find?
AThe shortest tree
BThe hyperplane with the maximum margin between classes โ
CThe nearest neighbours
DThe centroid of each cluster
๐ก ExplanationSVM maximises the distance between the hyperplane and the closest points (support vectors).
Question 14
What is the ‘kernel trick’ in SVM?
ARemoving features
BMapping data into a higher-dimensional space to make it linearly separable โ
CSpeeding up training
DReducing the dataset
๐ก ExplanationCommon kernels: linear, polynomial, RBF, sigmoid.
Question 15
K-means is an example of:
ASupervised classification
BUnsupervised clustering โ
CRegression
DReinforcement learning
๐ก ExplanationK-means partitions data into K clusters around centroids.
Question 16
In K-means, the algorithm stops when:
AAccuracy reaches 100%
BCentroids no longer move significantly โ
CK equals the number of points
DThe tree is fully grown
๐ก ExplanationIt iterates assign-and-update until convergence.
Question 17
Which metric evaluates a classification model by comparing predicted and actual labels in a table?
AR-squared
BConfusion matrix โ
CMSE
DSilhouette score
๐ก ExplanationFrom it you compute precision, recall and F1.
Question 18
Precision is defined as:
ATP / (TP + FN)
BTP / (TP + FP) โ
CTN / (TN + FP)
D(TP + TN) / total
๐ก ExplanationPrecision is the share of predicted positives that are correct.
Question 19
Recall is defined as:
ATP / (TP + FP)
BTP / (TP + FN) โ
CTN / (TN + FN)
DFP / (FP + TN)
๐ก ExplanationRecall is the share of actual positives that were found.
Question 20
Which Python library is mainly used for classical machine learning in the course?
ATensorFlow
Bscikit-learn โ
CPyTorch
DKeras
๐ก Explanationscikit-learn provides regression, classification, clustering and evaluation tools.
Question 21
What is overfitting?
AThe model is too simple
BThe model fits training data too closely and performs poorly on new data โ
CThe model trains too fast
DThe data is too large
๐ก ExplanationHigh training accuracy with low test accuracy signals overfitting.
Question 22
Which technique helps evaluate a model more reliably than a single train/test split?
AUsing all data for training
BK-fold cross-validation โ
CRemoving the test set
DIncreasing K in KNN
๐ก ExplanationEach fold serves once as the test set.
Next: Introduction to Deep Learning and Neural Networks with Keras โ
ย
๐ง
Course 2 โ Introduction to Deep Learning and Neural Networks with Keras (Questions 23โ42)
Neurons, forward and backpropagation, activations, Keras models, CNNs, RNNs and autoencoders
Question 23
What is an artificial neuron’s output computed from?
AThe sum of inputs only
BA weighted sum of inputs plus a bias, passed through an activation function โ
CA random number
DThe number of layers
๐ก Explanationz = w.x + b, then a = f(z).
Question 24
What is forward propagation?
AUpdating weights
BPassing input data through the network layer by layer to produce an output โ
CShuffling data
DRemoving neurons
๐ก ExplanationEach layer transforms the previous layer’s output.
Question 25
What is backpropagation?
AMoving data backwards to the user
BComputing gradients of the loss with respect to weights and propagating them backward to update weights โ
CDeleting layers
DNormalising inputs
๐ก ExplanationIt applies the chain rule from the output layer back to the input.
Question 26
What does gradient descent do?
AIncreases the loss
BIteratively adjusts weights in the direction that reduces the loss โ
CChooses the activation function
DAdds layers
๐ก ExplanationThe learning rate controls the step size.
Question 27
What is the ‘vanishing gradient’ problem?
AGradients become too large
BGradients become very small in early layers, slowing or stopping learning โ
CWeights are deleted
DThe dataset is too small
๐ก ExplanationIt occurs with sigmoid/tanh activations in deep networks.
Question 28
Which activation function helps overcome the vanishing gradient problem?
ASigmoid
BReLU โ
CTanh
DStep function
๐ก ExplanationReLU outputs max(0, x) and does not saturate for positive inputs.
Question 29
The softmax function is typically used in:
AHidden layers
BThe output layer for multi-class classification โ
CThe input layer
DRegression outputs
๐ก ExplanationIt converts scores into probabilities that sum to 1.
Question 30
In Keras, which class is used to build a model layer by layer?
ASequential โ
BFunctional
CPipeline
DLayerwise
๐ก Explanationmodel = Sequential(); model.add(Dense(…)).
Question 31
Which Keras layer is a fully connected layer?
AConv2D
BDense โ
CMaxPooling2D
DLSTM
๐ก ExplanationDense connects every input to every output neuron.
Question 32
For a regression model in Keras, a common loss function is:
Acategorical_crossentropy
Bmean_squared_error โ
Cbinary_crossentropy
Dhinge
๐ก ExplanationMSE is standard for continuous targets.
Question 33
For multi-class classification in Keras, a common loss function is:
Amean_squared_error
Bcategorical_crossentropy โ
Cmean_absolute_error
Dhuber
๐ก ExplanationUsed with a softmax output layer.
Question 34
Which optimiser is most commonly used as a default in Keras?
ASGD
BAdam โ
CAdagrad
DMomentum
๐ก ExplanationAdam adapts the learning rate for each parameter.
Question 35
What is an ‘epoch’?
AOne weight update
BOne complete pass through the entire training dataset โ
COne layer
DOne batch
๐ก ExplanationTraining usually runs for many epochs.
Question 36
What is a ‘shallow’ vs ‘deep’ neural network?
AShallow has one hidden layer; deep has many โ
BShallow uses images; deep uses text
CShallow is slower
DNo difference
๐ก ExplanationDepth lets networks learn hierarchical features.
Question 37
What is a Convolutional Neural Network (CNN) best suited for?
ATabular data
BImage data โ
CTime series only
DText only
๐ก ExplanationConvolution and pooling layers extract spatial features.
Question 38
What does a pooling layer do in a CNN?
AAdds parameters
BReduces spatial dimensions and computation โ
CIncreases image size
DNormalises colours
๐ก ExplanationMax pooling keeps the largest value in each window.
Question 39
What is a Recurrent Neural Network (RNN) designed for?
AImages
BSequential data such as text and time series โ
CTabular data
DClustering
๐ก ExplanationRNNs keep a hidden state across time steps.
Question 40
What is an LSTM?
AA type of CNN
BA recurrent network with gates that handles long-term dependencies โ
CAn optimiser
DA loss function
๐ก ExplanationLong Short-Term Memory networks mitigate vanishing gradients in sequences.
Question 41
What is an autoencoder?
AA supervised classifier
BAn unsupervised network that learns to compress and reconstruct its input โ
CAn optimiser
DA pooling layer
๐ก ExplanationUsed for dimensionality reduction and denoising.
Question 42
What does ‘dropout’ do?
ADeletes the dataset
BRandomly disables neurons during training to reduce overfitting โ
CSpeeds up inference
DIncreases learning rate
๐ก ExplanationA regularisation technique.
Next: Deep Learning with Keras and TensorFlow โ
ย
๐ถ
Course 3 โ Deep Learning with Keras and TensorFlow (Questions 43โ54)
TensorFlow 2, transfer learning, callbacks, Functional API, transformers, GANs and diffusion
Question 43
In TensorFlow 2, which mode is enabled by default?
AGraph mode
BEager execution โ
CLazy mode
DStatic mode
๐ก ExplanationEager execution evaluates operations immediately.
Question 44
What is a tensor?
AA type of neuron
BA multi-dimensional array โ
CA loss function
DA dataset
๐ก ExplanationScalars, vectors and matrices are tensors of rank 0, 1 and 2.
Question 45
What is transfer learning in deep learning?
ATraining from scratch
BReusing a pre-trained model’s weights for a new but related task โ
CMoving data between GPUs
DCopying datasets
๐ก ExplanationCommon with ImageNet-trained models such as VGG16 and ResNet.
Question 46
When fine-tuning a pre-trained model, ‘freezing’ layers means:
ADeleting them
BKeeping their weights fixed during training โ
CDoubling them
DRandomising them
๐ก ExplanationUsually early layers are frozen and later layers trained.
Question 47
What is data augmentation?
ABuying more data
BCreating modified versions of training data, such as rotated or flipped images โ
CRemoving outliers
DCompressing data
๐ก ExplanationIt improves generalisation.
Question 48
What does a Keras ‘callback’ such as EarlyStopping do?
AStarts training early
BStops training when a monitored metric stops improving โ
CSkips layers
DDeletes checkpoints
๐ก ExplanationPrevents overfitting and saves time.
Question 49
What is the Keras Functional API used for?
AOnly simple stacks
BModels with multiple inputs/outputs or non-linear topology โ
CData loading
DPlotting
๐ก ExplanationMore flexible than Sequential.
Question 50
What is batch normalisation?
ANormalising labels
BNormalising layer inputs per mini-batch to stabilise and speed training โ
CShuffling batches
DReducing batch size
๐ก ExplanationIt also has a mild regularising effect.
Question 51
What is a Transformer’s key mechanism?
AConvolution
BSelf-attention โ
CPooling
DRecurrence
๐ก ExplanationSelf-attention relates every token to every other token.
Question 52
What is a GAN?
AA regression model
BTwo networks, a generator and a discriminator, trained in competition โ
CA clustering algorithm
DAn optimiser
๐ก ExplanationGenerative Adversarial Networks produce realistic synthetic data.
Question 53
What is a diffusion model?
AA classifier
BA generative model that learns to reverse a gradual noising process โ
CA pooling method
DA tokeniser
๐ก ExplanationUsed for image generation.
Question 54
What is ‘reinforcement learning’ with Keras/TensorFlow typically used for in the course?
AImage classification
BTraining agents (e.g. Q-learning) to maximise reward โ
CClustering
DTranslation
๐ก ExplanationDeep Q-Networks combine Q-learning with neural networks.
Next: Neural Networks and Deep Learning with PyTorch โ
ย
๐ฅ
Courses 4โ5 โ Neural Networks and Deep Learning with PyTorch (Questions 55โ70)
Tensors, autograd, nn.Module, DataLoader, losses, optimisers and CNNs in PyTorch
Question 55
In PyTorch, what is a tensor’s ‘requires_grad’ attribute for?
APrinting the tensor
BTelling autograd to track operations for gradient computation โ
CChanging its shape
DMoving it to GPU
๐ก ExplanationSet requires_grad=True for parameters you want to optimise.
Question 56
Which method computes gradients in PyTorch?
A.forward()
B.backward() โ
C.step()
D.zero_grad()
๐ก Explanationloss.backward() populates .grad on tensors.
Question 57
What does optimizer.step() do?
AComputes the loss
BUpdates parameters using the computed gradients โ
CResets gradients
DLoads data
๐ก ExplanationCalled after loss.backward().
Question 58
Why call optimizer.zero_grad() each iteration?
ATo delete the model
BBecause gradients accumulate by default โ
CTo increase speed
DTo shuffle data
๐ก ExplanationWithout it, gradients from previous batches add up.
Question 59
Which PyTorch class do you subclass to define a custom model?
Atorch.Tensor
Btorch.nn.Module โ
Ctorch.optim.SGD
Dtorch.utils.Data
๐ก ExplanationYou define layers in __init__ and the computation in forward().
Question 60
What do Dataset and DataLoader do in PyTorch?
ADefine the model
BDataset wraps the data; DataLoader batches and shuffles it โ
CCompute gradients
DPlot results
๐ก ExplanationDataLoader(dataset, batch_size=…, shuffle=True).
Question 61
Which loss function is used for multi-class classification in PyTorch?
Ann.MSELoss
Bnn.CrossEntropyLoss โ
Cnn.L1Loss
Dnn.BCELoss
๐ก ExplanationIt combines LogSoftmax and NLLLoss.
Question 62
Which loss is used for linear regression in PyTorch?
Ann.CrossEntropyLoss
Bnn.MSELoss โ
Cnn.NLLLoss
Dnn.BCELoss
๐ก ExplanationMean squared error.
Question 63
What is mini-batch gradient descent?
AUsing the whole dataset per update
BUpdating weights using small subsets of the data โ
CUsing one sample per update
DNo updates
๐ก ExplanationA balance between batch and stochastic gradient descent.
Question 64
What does torch.nn.Linear(in_features, out_features) create?
AA convolution layer
BA fully connected (linear) layer โ
CAn activation
DA loss
๐ก ExplanationIt applies y = xA^T + b.
Question 65
What is the purpose of a validation set?
AFinal testing
BTuning hyperparameters and monitoring overfitting during training โ
CTraining
DDeployment
๐ก ExplanationThe test set is kept for the final unbiased estimate.
Question 66
How do you move a PyTorch model to a GPU?
Amodel.gpu()
Bmodel.to(‘cuda’) โ
Cmodel.fast()
Dmodel.device()
๐ก ExplanationTensors must be moved to the same device.
Question 67
What is ‘momentum’ in optimisation?
AA type of loss
BA term that accelerates gradient descent by accumulating past gradients โ
CA regulariser
DA data loader
๐ก ExplanationIt helps escape shallow minima and smooths updates.
Question 68
What is the softmax regression model used for?
ARegression
BMulti-class classification โ
CClustering
DGeneration
๐ก ExplanationIt generalises logistic regression to many classes.
Question 69
In a CNN in PyTorch, nn.Conv2d’s ‘kernel_size’ sets:
AThe number of classes
BThe size of the filter window โ
CThe learning rate
DThe batch size
๐ก ExplanationStride and padding control the output size.
Question 70
What does model.eval() do?
ATrains the model
BSets layers like dropout and batch norm to evaluation mode โ
CDeletes gradients
DSaves the model
๐ก ExplanationUse torch.no_grad() as well during inference.
Next: Generative AI, LLMs and Fine-Tuning Transformers โ
ย
๐ฌ
Courses 7โ11 โ Generative AI, LLMs and Fine-Tuning Transformers (Questions 71โ88)
Tokenization, embeddings, GPT vs BERT, attention, PEFT, LoRA, QLoRA and quantization
Question 71
What is a large language model (LLM)?
AA database
BA transformer-based model trained on huge text corpora to understand and generate language โ
CA search index
DA tokenizer
๐ก ExplanationExamples: GPT, Llama, IBM Granite.
Question 72
What is tokenization?
AEncrypting text
BSplitting text into tokens (words or sub-words) that a model can process โ
CTranslating text
DSummarising text
๐ก ExplanationMethods include word-based, character-based and sub-word (BPE, WordPiece).
Question 73
What is an embedding?
AA compressed file
BA dense vector that represents the meaning of a token or text โ
CA type of loss
DA layer of dropout
๐ก ExplanationSimilar meanings have nearby vectors.
Question 74
Which architecture uses only a decoder and is used for text generation?
ABERT
BGPT โ
CWord2Vec
DCNN
๐ก ExplanationGPT models are autoregressive decoders.
Question 75
Which architecture uses only an encoder and suits understanding tasks?
๐ก ExplanationBERT is trained with masked language modelling.
Question 76
What is positional encoding in a transformer?
AA loss function
BInformation added to embeddings so the model knows token order โ
CA tokeniser
DAn optimiser
๐ก ExplanationSelf-attention alone is order-agnostic.
Question 77
What is self-attention?
APaying attention to the user
BA mechanism that weighs the relevance of every token to every other token in a sequence โ
CA pooling method
DA regulariser
๐ก ExplanationIt captures long-range dependencies.
Question 78
What is fine-tuning an LLM?
ATraining from scratch
BFurther training a pre-trained model on task-specific data โ
CShrinking a model
DTokenising data
๐ก ExplanationAdapts general knowledge to a domain.
Question 79
What is PEFT?
AA dataset
BParameter-Efficient Fine-Tuning: updating a small number of parameters instead of the whole model โ
CA tokenizer
DA metric
๐ก ExplanationIt cuts compute and storage costs.
Question 80
What is LoRA?
AA loss function
BLow-Rank Adaptation: adding small trainable low-rank matrices to frozen weights โ
CA dataset format
DA prompt style
๐ก ExplanationA popular PEFT method.
Question 81
What is QLoRA?
ALoRA with quantised (e.g. 4-bit) base model weights to reduce memory โ
BA query language
CA tokenizer
DA new architecture
๐ก ExplanationIt enables fine-tuning large models on modest hardware.
Question 82
What is quantization?
AAdding layers
BReducing the numerical precision of model weights to shrink size and speed inference โ
CTokenising
DClustering
๐ก ExplanationFor example from 32-bit floats to 8-bit or 4-bit.
Question 83
What is instruction tuning?
ATuning hyperparameters
BFine-tuning a model on instruction-response pairs so it follows prompts better โ
CPruning
DQuantising
๐ก ExplanationIt improves zero-shot task following.
Question 84
What is RLHF?
AA tokenizer
BReinforcement Learning from Human Feedback โ
CA dataset
DA pooling layer
๐ก ExplanationHuman preference signals train a reward model that guides the LLM.
Question 85
Which library is widely used to load pre-trained transformers?
Ascikit-learn
BHugging Face Transformers โ
COpenCV
DMatplotlib
๐ก ExplanationIt provides models, tokenizers and pipelines.
Question 86
What is in-context learning?
ARetraining the model
BThe model adapting to a task from examples given in the prompt without weight updates โ
CFine-tuning
DQuantising
๐ก ExplanationFew-shot prompting is in-context learning.
Question 87
What is perplexity?
AA tokeniser
BA measure of how well a language model predicts a sample; lower is better โ
CA layer
DAn optimiser
๐ก ExplanationIt is the exponential of the average negative log-likelihood.
Question 88
What does ‘temperature’ control during generation?
AHardware heat
BThe randomness of the sampled output โ
CModel size
DBatch size
๐ก ExplanationLower values make output more deterministic.
Next: RAG, LangChain and AI Agents โ
ย
๐
Courses 12โ13 โ RAG, LangChain and AI Agents (Questions 89โ102)
Retrieval-augmented generation, vector databases, chains, agents and the capstone app
Question 89
What does RAG stand for?
ARandom Answer Generator
BRetrieval-Augmented Generation โ
CRecurrent Attention Graph
DRapid AI Gateway
๐ก ExplanationRAG retrieves relevant documents and passes them to the LLM as context.
Question 90
Why use RAG?
ATo make models smaller
BTo ground answers in up-to-date or private data and reduce hallucination โ
CTo speed up training
DTo replace tokenisation
๐ก ExplanationThe model does not need retraining when the knowledge changes.
Question 91
What is a vector database used for in RAG?
AStoring images
BStoring embeddings and retrieving the most similar chunks to a query โ
CTraining models
DTokenising text
๐ก ExplanationExamples: Chroma, FAISS, Milvus.
Question 92
What is ‘chunking’ in a RAG pipeline?
ADeleting documents
BSplitting documents into smaller pieces before embedding โ
CMerging answers
DCompressing models
๐ก ExplanationChunk size and overlap affect retrieval quality.
Question 93
What is LangChain?
AA blockchain
BA framework for building LLM applications by chaining prompts, models, retrievers and tools โ
CA tokenizer
DA GPU
๐ก ExplanationIt provides chains, agents, memory and document loaders.
Question 94
In LangChain, what is a ‘chain’?
AA dataset
BA sequence of calls (prompt, model, parser) linked together โ
CA GPU cluster
DA loss function
๐ก ExplanationLCEL uses the pipe operator to compose them.
Question 95
What is an AI agent?
AA human operator
BAn LLM-driven system that decides which tools or actions to use to reach a goal โ
CA dataset
DA tokenizer
๐ก ExplanationAgents plan, call tools and observe results in a loop.
Question 96
What is a ‘prompt template’?
AA fixed answer
BA reusable prompt with placeholders filled at run time โ
CA model checkpoint
DA tokenizer file
๐ก ExplanationIt keeps prompts consistent across calls.
Question 97
What does a ‘retriever’ do in RAG?
AGenerates text
BFinds the most relevant documents for a query โ
CTrains the model
DEvaluates accuracy
๐ก ExplanationUsually via similarity search over embeddings.
Question 98
Which similarity measure is common for comparing embeddings?
AHamming distance
BCosine similarity โ
CJaccard index
DEdit distance
๐ก ExplanationIt compares the angle between vectors.
Question 99
What is ‘memory’ in a LangChain application?
AGPU RAM
BStored conversation history that gives the model context across turns โ
CDisk space
DThe training set
๐ก ExplanationBuffer and summary memory are common types.
Question 100
What is Gradio used for in the capstone projects?
ATraining models
BBuilding a simple web interface for a model or app โ
CTokenising
DQuantising
๐ก ExplanationIt lets you demo an app in a few lines of Python.
Question 101
What is a hallucination in a RAG system usually a sign of?
AToo many GPUs
BPoor retrieval or the model ignoring the provided context โ
CLow temperature
DToo many chunks
๐ก ExplanationBetter chunking, retrieval and prompts reduce it.
Question 102
What is the role of an ‘output parser’ in LangChain?
ATokenising input
BConverting the model’s raw text into a structured format such as JSON โ
CEmbedding documents
DTraining
๐ก ExplanationIt makes outputs usable by downstream code.
๐ The 13 courses in the IBM AI Engineering Professional Certificate
1. Machine Learning with Python
2. Introduction to Deep Learning & Neural Networks with Keras
3. Deep Learning with Keras and TensorFlow
4. Introduction to Neural Networks and PyTorch
5. Deep Learning with PyTorch
6. AI Capstone Project with Deep Learning
7. Generative AI and LLMs: Architecture and Data Preparation
8. Gen AI Foundational Models for NLP & Language Understanding
9. Generative AI Language Modeling with Transformers
10. Generative AI Engineering and Fine-Tuning Transformers
11. Generative AI Advanced Fine-Tuning for LLMs
12. Fundamentals of AI Agents Using RAG and LangChain
13. Project: Generative AI Applications with RAG and LangChain
Course line-up as listed on Coursera; IBM updates it periodically, so check the certificate page for the current order.
๐ฅ Download all 102+ AI Engineering quiz MCQs as PDF (free)
๐ฏ More IBM and AI certification MCQs
Question banks updated regularly to match the latest course content
[…] a short explanation under every question. For the deep-learning and generative-AI track, see the IBM AI Engineering Professional Certificate answers; for a no-code start, see IBM AI Fundamentals. A free PDF of the full set is at the end of the […]
[…] practice for the Cisco Networking Academy versionNetAcad course ยท same IBM badgeOpen answers โ๐ ๏ธ IBM AI Engineering Professional Certificate100+ MCQs: ML with Python, Keras, TensorFlow, PyT…๐ IBM Machine Learning Professional Certificate90+ MCQs: EDA, regression, classification, […]