GradePack

    • Home
    • Blog
Skip to content
bg
bg
bg
bg

GradePack

Question 8: (12 points) Consider the best practices for trai…

Question 8: (12 points) Consider the best practices for training neural networks. Answer the following questions: (3 points) In practice, the Nesterov momentum often converges faster than the standard momentum. Explain why the correction based on the gradient at the anticipated position might prevent overshooting. (6 points) You observe the following training behaviors: Observation 1: Your deep network (8 layers) trains very slowly. The gradients in early layers are extremely small. Training loss decreases but very gradually. Observation 2: Your network achieves 99\% training accuracy but only 70\% validation accuracy. The gap is large and consistent. Observation 3: Your network’s training is unstable – loss fluctuates wildly and sometimes diverges. Different random initializations lead to very different outcomes. For each observation: (i) Identify whether dropout, batch normalization, or both would help, and (ii) Explain why the chosen technique addresses the specific problem.   3. (3 points) Consider a feedforward neural network with the following architecture: Input (100 features) → Dense(256) → ReLU → Dense(128) → ReLU → Dense(10) → Softmax. Calculate the total number of trainable parameters in this network. Show your work by computing the parameters for each layer separately, including both weights and biases.

Read Details

Question 5: (13 points) Consider a dataset of N samples whe…

Question 5: (13 points) Consider a dataset of N samples where each

Read Details

Explain why relying on children’s eyewitness accounts may be…

Explain why relying on children’s eyewitness accounts may be problematic. Also, outline under what conditions children’s accounts are most accurate. (9 points.)

Read Details

A good night’s sleep is most likely to improve exam grades b…

A good night’s sleep is most likely to improve exam grades by supporting the process of

Read Details

Question 1: (11 points) Consider a binary classification pro…

Question 1: (11 points) Consider a binary classification problem with D-dimensional samples. Let and be the mean vectors for the two classes, the within-class scatter matrix, and

Read Details

The MMPI is an example of a

The MMPI is an example of a

Read Details

Question 4: (12 points) Consider a binary classification pro…

Question 4: (12 points) Consider a binary classification problem with labels

Read Details

The monoamine oxidase A (MAOA) gene, sometimes called the “w…

The monoamine oxidase A (MAOA) gene, sometimes called the “warrior gene”

Read Details

At one time Jimmy was scared of dogs because he was bitten b…

At one time Jimmy was scared of dogs because he was bitten by one. With subsequent repeated exposure to tame dogs in safe settings, however, his fear of dogs has gradually faded. Jimmy’s diminishing fear of dogs best illustrates

Read Details

​ Clive Wearing had _______________ and ___________________…

​ Clive Wearing had _______________ and ___________________ amnesia.  This made it impossible for him to form new and some past memories.  His __________________, ______________________, and _________________________ parts of his brin were intact allowing him to remember his love of Deborah (his wife) and how to play the piano.  These parts later allowed him to learn how to go to the kitchen and make a cup of tea if he were asked to do so without conscious knowledge that he had learned how and where.

Read Details

Posts pagination

Newer posts 1 … 55 56 57 58 59 … 72,323 Older posts

GradePack

  • Privacy Policy
  • Terms of Service
Top