You have a dataset of face images at 128×128 resolution, some are severely noisy (grainy camera shots). You want to classify each image into one of five expressions: happy, sad, angry, surprised, neutral. You decide to build: Autoencoder (AE) for denoising. CNN that classifies the AE’s output. GAN for data augmentation—generating extra images in each expression category. After some early success, you suspect domain mismatch and overfitting. Let’s see what goes wrong. — Angry is the smallest class in the dataset. You generate GAN samples to augment. A post-hoc analysis shows some generated “angry” faces look more “cartoonish” or “mildly annoyed” than truly “angry.” Which statements about possible solutions are valid?

John’s parents never go to his school conferences or make sure he has his homework. They are uninvolved with any aspect of his life. This is an example of ____________ type of parenting.                       

_________________ is an educational program intended for “at risk” pre-school children. Is an attempt to help these students increase their “school skills” so they won’t be as far behind.       

Your model uses self-attention for machine translation. Which claims about attention are valid? (Select all that apply)

Now your dataset has short video clips of faces showing an expression transition (e.g., neutral → smile). Some clips are shot in low-light conditions. You attempt: GAN to brighten or color-correct frames, AE for further denoising or super-resolution, CNN (or 3D CNN) for expression classification across frames. After some usage, you realize certain frames come out “over-bright” or “washed out.” — XYZ

Scenario: A 68-year-old patient is admitted to the ICU with cardiogenic shock following a severe myocardial infarction. During your assessment, you collect the following information: Blood pressure of 85/50 mmHgHeart rate of 120 beats per minuteRespiratory rate of 28 breaths per minuteUrine output of 15 mL/hrIncreased AST and ALTAltered mental status When caring for this patient, which information collected by the nurse indicates that the patient may be developing multiple organ dysfunction syndrome (MODS)? Select all that apply.

Unlike GANs and VAEs, standard autoencoders (AEs) struggle to generate new realistic samples from scratch.What is the fundamental reason for this limitation? (Select one correct answer)

Now your dataset has short video clips of faces showing an expression transition (e.g., neutral → smile). Some clips are shot in low-light conditions. You attempt: GAN to brighten or color-correct frames, AE for further denoising or super-resolution, CNN (or 3D CNN) for expression classification across frames. After some usage, you realize certain frames come out “over-bright” or “washed out.” — You’ve published a streaming app that can “clean up” people’s faces in real time and detect expressions. Some users claim it’s misrepresenting them by brightening or altering features. One constructive approach?

PART I – THEORETICAL AND FOUNDATIONAL KNOWLEDGE CNNs learn hierarchical features, starting with edges and evolving into complex object representations.If you randomly shuffle pixels in images without modifying their intensity values, which part of a CNN’s feature hierarchy is most affected? (Select the best answer)

A nurse is caring for a laboring patient who is at 6 cm dilation, 90% effaced, and experiencing contractions every 3-4 minutes, each lasting 60 seconds. In which stage and phase of labor is the patient?