Этот материал находится в платной подписке. Оформи премиум подписку и смотри или слушай Deep Learning Interview Prep Course | Full Course [100 Q&A's], а также все другие курсы, прямо сейчас!
Премиум
  • Урок 1. 00:04:07
    Q1 - What is Deep Learning?
  • Урок 2. 00:04:14
    Q2 - What is Deep Learning?
  • Урок 3. 00:07:14
    Q3 - What is a Neural Network?
  • Урок 4. 00:03:34
    Q4 - Explain the concept of a neuron in Deep Learning.
  • Урок 5. 00:07:53
    Q5 - Explain architecture of Neural Networks in simple way
  • Урок 6. 00:04:01
    Q6 - What is an activation function in a Neural Network?
  • Урок 7. 00:13:43
    Q7 - Name few popular activation functions and describe them
  • Урок 8. 00:01:27
    Q8 - What happens if you do not use any activation functions in a NN?
  • Урок 9. 00:05:53
    Q9 - Describe how training of basic Neural Networks works
  • Урок 10. 00:10:41
    Q10 - What is Gradient Descent?
  • Урок 11. 00:05:34
    Q11 - What is the function of an optimizer in Deep Learning?
  • Урок 12. 00:08:39
    Q12 - What is backpropagation, and why is it important in Deep Learning?
  • Урок 13. 00:03:05
    Q13 - How is backpropagation different from gradient descent?
  • Урок 14. 00:07:01
    Q14 - Describe what Vanishing Gradient Problem is and it’s impact on NN
  • Урок 15. 00:08:31
    Q15 - Describe what Exploding Gradients Problem is and it’s impact on NN
  • Урок 16. 00:04:40
    Q16 - There is a neuron results in a large error in backpropagation. Reason?
  • Урок 17. 00:06:18
    Q17 - What do you understand by a computational graph?
  • Урок 18. 00:06:39
    Q18 - What is Loss Function and what are various Loss functions used in DL?
  • Урок 19. 00:03:41
    Q19 - What is Cross Entropy loss function and how is it called in industry?
  • Урок 20. 00:03:40
    Q20 - Why is Cross-entropy preferred as cost function for multi-class classification?
  • Урок 21. 00:06:11
    Q21 - What is SGD and why it’s used in training Neural Networks?
  • Урок 22. 00:05:52
    Q22 - Why does stochastic gradient descent oscillate towards local minima?
  • Урок 23. 00:05:19
    Q23: How is GD different from SGD
  • Урок 24. 00:06:04
    Q24: What is SGD with Momentum
  • Урок 25. 00:05:27
    Q25 - Batch Gradient Descent, Minibatch Gradient Descent vs SGD
  • Урок 26. 00:06:49
    Q26: What is impact of Batch Size
  • Урок 27. 00:04:10
    Q27: Batch Size vs Model Performance
  • Урок 28. 00:04:39
    Q28: What is Hessian, usage in DL
  • Урок 29. 00:05:29
    Q29: What is RMSProp and how does it work?
  • Урок 30. 00:04:33
    Q30: What is Adaptive Learning
  • Урок 31. 00:07:03
    Q31: What is Adam Optimizer
  • Урок 32. 00:04:53
    Q32: What is AdamW Algorithm in Neural Networks
  • Урок 33. 00:08:32
    Q33: What is Batch Normalization
  • Урок 34. 00:03:39
    Q34: What is Layer Normalization
  • Урок 35. 00:09:23
    Q35: What are Residual Connections
  • Урок 36. 00:03:41
    Q36: What is Gradient Clipping
  • Урок 37. 00:04:05
    Q37: What is Xavier Initialization
  • Урок 38. 00:03:16
    Q38: What are ways to solve Vanishing Gradients
  • Урок 39. 00:01:12
    Q39: How to solve Exploding Gradient Problem
  • Урок 40. 00:02:39
    Q40: What is Overfitting
  • Урок 41. 00:05:19
    Q41: What is Dropout
  • Урок 42. 00:00:42
    Q42: How does Dropout prevent Overfitting in Neural Networks
  • Урок 43. 00:04:42
    Q43: Is Dropout like Random Forest
  • Урок 44. 00:02:36
    Q44: What is the impact of DropOut on the training vs testing
  • Урок 45. 00:03:19
    Q45: What are L2 and L1 Regularizations for Overfitting NN
  • Урок 46. 00:04:05
    Q46: What is the difference between L1 and L2 Regularisations
  • Урок 47. 00:01:52
    Q47: How do L1 vs L2 Regularization impact the Weights in a NN?
  • Урок 48. 00:02:28
    Q48: What is the Curse of Dimensionality in Machine Learning | Deep Learning Interview Question
  • Урок 49. 00:04:05
    Q49 - How Deep Learning models tackle the Curse of Dimensionality | Deep Learning Interview Question
  • Урок 50. 00:02:58
    Q50: What are Generative Models, give examples?
  • Урок 51. 00:03:04
    Q51 - What are Discriminative Models, give examples?
  • Урок 52. 00:08:35
    Q52 - What is the difference between generative and discriminative models?
  • Урок 53. 00:04:31
    Q53 - What are Autoencoders and How Do They Work?
  • Урок 54. 00:04:32
    Q54: What is the Difference Beetween Autoenconders and other Neural Networks?
  • Урок 55. 00:01:25
    Q55 - What are some popular autoencoders, mention few?
  • Урок 56. 00:01:04
    Q56 - What is the role of the Loss function in Autoencoders, & how is it different from other NN?
  • Урок 57. 00:02:21
    Q57 - How do autoencoders differ from (PCA)?
  • Урок 58. 00:03:27
    Q58 - Which one is better for reconstruction linear autoencoder or PCA?
  • Урок 59. 00:06:31
    Q59 - How can you recreate PCA with neural networks?
  • Урок 60. 00:10:36
    Q60 - Can You Explain How Autoencoders Can be Used for Anomaly Detection?
  • Урок 61. 00:02:20
    Q61 - What are some applications of AutoEncoders
  • Урок 62. 00:04:09
    Q62 - How can uncertainty be introduced into Autoencoders, & what are the benefits and challenges of doing so?
  • Урок 63. 00:03:18
    Q63 - Can you explain what VAE is and describe its training process?
  • Урок 64. 00:03:48
    Q64 - Explain what Kullback-Leibler (KL) divergence is & why does it matter in VAEs?
  • Урок 65. 00:01:02
    Q65 - Can you explain what reconstruction loss is & it’s function in VAEs?
  • Урок 66. 00:04:35
    Q66 - What is ELBO & What is this trade-off between reconstruction quality & regularization?
  • Урок 67. 00:03:49
    Q67 - Can you explain the training & optimization process of VAEs?
  • Урок 68. 00:03:12
    Q68 - How would you balance reconstruction quality and latent space regularization in a practical Variational Autoencoder implementation?
  • Урок 69. 00:04:15
    Q69 - What is Reparametrization trick and why is it important?
  • Урок 70. 00:01:45
    Q70 - What is DGG "Deep Clustering via a Gaussian-mixture Variational Autoencoder (VAE)” with Graph Embedding
  • Урок 71. 00:02:24
    Q71 - How does a neural network with one layer and one input and output compare to a logistic regression?
  • Урок 72. 00:01:06
    Q72 - In a logistic regression model, will all the gradient descent algorithms lead to the same model if run for a long time?
  • Урок 73. 00:05:10
    Q73 - What is a Convolutional Neural Network?
  • Урок 74. 00:02:02
    Q74 - What is padding and why it’s used in Convolutional Neural Networks (CNNs)?
  • Урок 75. 00:13:18
    Q75 - Padded Convolutions: What are Valid and Same Paddings?
  • Урок 76. 00:05:43
    Q76 - What is stride in CNN and why is it used?
  • Урок 77. 00:02:28
    Q77 - What is the impact of Stride size on CNNs?
  • Урок 78. 00:09:12
    Q78 - What is Pooling, what is the intuition behind it and why is it used in CNNs?
  • Урок 79. 00:02:49
    Q79 - What are common types of pooling in CNN?
  • Урок 80. 00:03:47
    Q80 - Why min pooling is not used?
  • Урок 81. 00:01:36
    Q81 - What is translation invariance and why is it important?
  • Урок 82. 00:02:55
    Q82 - How does a 1D Convolutional Neural Network (CNN) work?
  • Урок 83. 00:07:09
    Q83 - What are Recurrent Neural Networks, and walk me through the architecture of RNNs.
  • Урок 84. 00:01:30
    Q84 - What are the main disadvantages of RNNs, especially in Machine Translation Tasks?
  • Урок 85. 00:06:16
    Q85 - What are some applications of RNN?
  • Урок 86. 00:05:05
    Q86 - What technique is commonly used in RNNs to combat the Vanishing Gradient Problem?
  • Урок 87. 00:05:24
    Q87 - What are LSTMs and their key components?
  • Урок 88. 00:06:16
    Q88 - What limitations of RNN that LSTMs do and don’t address and how?
  • Урок 89. 00:03:35
    Q89 - What is a gated recurrent unit (GRU) and how is it different from LSTMs?
  • Урок 90. 00:06:17
    Q90 - Describe how Generative Adversarial Networks (GANs) work and the roles of the generator and discriminator in learning.
  • Урок 91. 00:04:10
    Q91 - Describe how would you use GANs for image translation or creating photorealistic images?
  • Урок 92. 00:04:12
    Q92 - How would you address mode collapse and vanishing gradients in GAN training, and what is their impact on data quality?
  • Урок 93. 00:09:04
    Q93- Minimax and Nash Equilibrium in GAN
  • Урок 94. 00:06:01
    Q94 - What are token embeddings and what is their function?
  • Урок 95. 00:11:26
    Q95 - What is self-attention mechanism?
  • Урок 96. 00:06:54
    Q96 - What is Multi-Head Self-Attention and how does it enable more effective processing of sequences in Transformers?
  • Урок 97. 00:05:52
    Q97 - What are transformers and why are they important in combating problems of models like RNN and LSTMs?
  • Урок 98. 00:08:56
    Q98 - Walk me through the architecture of transformers.
  • Урок 99. 00:05:48
    Q99 - What are positional encodings and how are they calculated?
  • Урок 100. 00:02:13
    Q100 - Why do we add positional encodings to Transformers but not to