#Deep_Learning

Question count - 0     Last updated    - V4 (09-Aug-2024)

What is Deep Learning?

What Is a Multi-layer Perceptron(MLP)?

What Is the Role of Activation Functions in a Neural Network?

What is the meaning of term weight initialization in neural networks?

What is the use of the Activation function?

What is a binary step function?

What is the sigmoid function?

What is Tanh function?

What is ReLU function?

What is the use of leaky ReLU function?

What is the softmax function?

What is a Swish function?

What is the most used activation function?

What is Model Capacity?

What is the cost function?

What is matrix element-wise multiplication? Explain with an example.

What is an RNN?

What is Vanishing Gradient?

What is Exploding Gradient?

What is Single-Layer Perceptron?

What is Multilayer Perceptrons?

What are the main differences between AI, Machine Learning, and Deep Learning?

What are the applications of deep learning?

What are the deep learning frameworks or tools?

What are the disadvantages of deep learning?

What are the prerequisites for starting in Deep Learning?

What are the supervised learning algorithms in Deep learning?

What are the unsupervised learning algorithms in Deep learning?

What are the main benefits of Mini-batch Gradient Descent?

What are the issues faced while training in Recurrent Networks?

What are the different layers of Autoencoders? Explain briefly.

What are the three steps to developing the necessary assumption structure in Deep learning?

Can Relu function be used in output layer?

Differentiate supervised and unsupervised deep learning procedures.

Do you think that deep network is better than a shallow one?

Explain Data Normalization.

Explain gradient descent ?

Explain the following variant of Gradient Descent: Stochastic, Batch, and Mini-batch?

Explain the different layers of CNN.

Explain the importance of LSTM.

How many layers in the neural network?

How many types of activation function are available?

In which layer softmax activation function used?

What do you understand by Autoencoder?

What do you mean by Dropout?

What do you understand by Tensors?

What do you understand by Boltzmann Machine?

What do you understand by a convolutional neural network?

What do you understand by Deep Autoencoders?

What do you understand by Perceptron? Also, explain its type.

Why is zero initialization not a good weight initialization process?

What is mean by deep learning?

What is the cost function?

What are the benefits of mini-batch gradient descent?

What is mean by gradient descent?

What is meant by a backpropagation?

What is means by convex hull?

What is means by auto-encoder?

What are the difference Algorithm techniques in Machine Learning?

What is the advantage of Naive Bayes?

What are the function using Supervised Learning?

What are the functions using Unsupervised Learning?

What are the roles of activation function?

What is Overfitting in Machine Learning?

What are the conditions when Overfitting happens?

What are the advantages of decision trees?

What are parametric models and Non-Parametric models?

What are some different cases uses of machine learning algorithms can be used?

What is bootstrap sampling?

What is permutation sampling?

What is total sum of squares?

What is sum of squares within?

What is sum of squares between?

What is p value?

What is R^2 value?

What does it mean to have a high R^2 value?

What are residuals in a regression model?

What are fitted values, calculate fitted value for Y=7X+8, when X =5?

What pattern should residual vs fitted plots show in a regression analysis?

What is overfitting and underfitting?

What is type 1 and type 2 errors?

What is ensemble learning?

What is the difference between supervised and unsupervised machine learning algorithms?

What is named entity recognition?

What is tf-idf?

What is the difference between regression and deep neural networks, is regression better than neural networks?

What is the use of activation functions in neural networks?

What is gradient descent?

What is learning rate in gradient descent?

What is a batch in deep neural networks?

What is an epoch in Deep neural networks?

What is stocastic gradient descent?

What is data normalization?

What is model capacity?

What is regularization?

What are hyper parameters in deep neural networks?

What is dropout in deep neural networks?

What are auto encodes?

What is homoscadasticity and heteroscadasticity?

What Are Hyperparameters?

What are some applications of Recurrent Neural Network?

What are the 2 layers of restricted Boltzmann machine called?

What Are the Applications of a Recurrent Neural Network (RNN)?

What are the five popular algorithms of machine learning?

What are the prerequisites for starting out in Deep Learning?

What Do You Understand by Backpropagation?

What does batch normalization do?

What is an algorithm in machine learning?

What is autoencoder?

What is classification?

What Is Dropout and Batch Normalization?

What is Fourier transform?

What is regression?

What Is the Boltzmann Machine?

What Is the Difference Between a Feedforward Neural Network and Recurrent Neural Network?

What is weight initialization in neural networks?

What Will Happen If the Learning Rate Is Set Too Low or Too High?

What is a Neural Network?

What Is Data Normalization, and Why Do We Need It?

What Is Deep Learning?

What is gradient descent in machine learning?

What is Machine Learning in industry.

What is dying neuron problem?

What is vanishing gradients?

What is exploding gradient descent?

What is ?overfitting? in the specific field?

What is univariate multivariate and bivariate analysis?

What is precision and recall?

What is the Difference Between AI, Machine Learning, and Deep Learning?

Name two activation functions used in deep neural networks?

Name the several initiatives used in the particular field

Why is batch normalization important?

Why are deep networks better than shallow ones?

Why do we use gradient descent?

Which data visualization libraries do you use and why they are useful?

which layer in a deep learning model would capture a more complex or higher order interaction?

How will do handle the missing data?

How do you understanding Machine Learning Concepts?

How can you avoid overfitting?

How does missing value imputation lead to selection bias?

How are node values calculated in a feed forward neural network?

How are the weights calculated which determine interactions in neural networks?

How does slope of tangent to the curve of loss function vs weigts help us in getting optimal weights for a neural network

How does ReLU activation function works? Define its value for -5 and +7

How can we normalize the data? State a method used for the same?

How many layers does Neural networks consist?

Where do you regularly source data-sets?

Difference between supervised and unsupervised machine learning?

Difference between adjusted R^2 and R^2

Difference between collinearity and correlation?

In case residual vs fitted plots is showing a pattern and is not distributed evenly or has some outliers how should it be handled?

Definition of Boltzmann Machine?

Do you have experience including Spark about big data tools for machine learning?

If in backward propagation you have gone through 9 iterations of calculating slopes and updated the weights simultaneously, how many times you must have done forward propagation?

Imagine a loss function vs weights plot depicting a gradient descent. At what point of the curve would we achieve optimal weights?

Imagine you have 2000 training samples and batch size is set to 200 how many iterations will it take to complete 1 epoch?

List some commercial practical applications of ANN?

List some real-life applications that involve deep learning?

State one of the finest procedures often utilized to overcome the issue of overfitting

Docker	Basics of Deep Learning Neural Network Architectures Training and Optimization Model Evaluation and Metrics Regularization Techniques Advanced Topics Practical Implementation Theory and Mathematics Real-world Applications Frameworks and Tools
Deep_Learning	Deep Learning Fundamentals Neural Network Terminology Feedforward Neural Networks Convolutional Neural Networks (CNNs) Recurrent Neural Networks (RNNs) Long Short-Term Memory (LSTM) Networks Gated Recurrent Units (GRUs) Autoencoders Generative Adversarial Networks (GANs) Transfer Learning
Deep_Learning	Activation Functions Loss Functions Optimization Algorithms Gradient Descent Stochastic Gradient Descent (SGD) Mini-Batch Gradient Descent Learning Rate Schedulers Batch Normalization Dropout Weight Initialization
Deep_Learning	Regularization Techniques Overfitting and Underfitting Cross-Validation Hyperparameter Tuning Epochs and Batches Backpropagation Vanishing and Exploding Gradients CNN Architectures (e.g., LeNet, AlexNet) Modern CNN Architectures (e.g., VGG, ResNet) Object Detection and Localization
Deep_Learning	Semantic Segmentation Image Classification Natural Language Processing (NLP) Word Embeddings Sequence-to-Sequence Models Attention Mechanisms Transformers BERT and GPT Models Text Generation Named Entity Recognition (NER)
Deep_Learning	Sentiment Analysis Machine Translation Speech Recognition Speech Synthesis Time Series Forecasting Anomaly Detection Dimensionality Reduction Principal Component Analysis (PCA) t-Distributed Stochastic Neighbor Embedding (t-SNE) Clustering with Deep Learning
Deep_Learning	Deep Reinforcement Learning Q-Learning Policy Gradient Methods Deep Q-Networks (DQN) Proximal Policy Optimization (PPO) Actor-Critic Methods Model-Free vs. Model-Based Reinforcement Learning Exploration vs. Exploitation Environment Simulation Reinforcement Learning Applications
Deep_Learning	Meta-Learning Few-Shot Learning Zero-Shot Learning Neural Architecture Search Neural Network Efficiency Model Compression Quantization Pruning Techniques Edge AI and Deployment Scalability in Deep Learning
Deep_Learning	Distributed Training Multi-GPU Training Data Augmentation Synthetic Data Generation Ethics in AI Bias and Fairness in Models Explainability and Interpretability Model Robustness Adversarial Attacks and Defenses Frameworks (e.g., TensorFlow, PyTorch)
Deep_Learning	Custom Layers and Operations GPU vs. CPU Computation Model Serving and APIs Experiment Tracking Reproducibility in Deep Learning Model Versioning Handling Imbalanced Datasets Feature Engineering for Deep Learning Hyperparameter Optimization Tools Model Evaluation Metrics
Deep_Learning	Error Analysis Deployment Pipelines Edge and IoT Device Considerations Scalable Infrastructure Large-Scale Data Handling Real-Time Inference Model Monitoring and Maintenance Security in Deep Learning Systems Current Trends and Research Future Directions in Deep Learning
Deep_Learning	Deep Learning Hardware Requirements Compute Resources Management Benchmarking Deep Learning Models Data Pipeline Engineering Data Preprocessing Techniques Handling Missing Data Feature Scaling Data Shuffling and Splitting Data Augmentation Strategies Synthetic Data and Simulations
Deep_Learning	Handling Noisy Data Class Imbalance Solutions Active Learning Semi-Supervised Learning Self-Supervised Learning Curriculum Learning Ensemble Methods Model Averaging Bagging and Boosting Stacking Models
Deep_Learning	Hyperparameter Search Methods Grid Search vs. Random Search Bayesian Optimization Automated Machine Learning (AutoML) Model Interpretability Techniques LIME (Local Interpretable Model-agnostic Explanations) SHAP (SHapley Additive exPlanations) Concept Drift and Adaptation Transfer Learning Strategies Domain Adaptation
Deep_Learning	Domain Generalization Pre-trained Models Usage Model Fine-Tuning Zero-Shot and Few-Shot Transfer Neural Network Transferability Knowledge Distillation Multi-Task Learning Multi-Label Classification Graph Neural Networks (GNNs) Graph Convolutional Networks (GCNs)
Deep_Learning	Graph Attention Networks (GATs) Node Classification Link Prediction Graph Embeddings Spatial and Temporal Data Analysis Dynamic Time Warping Sequence Modeling Techniques Temporal Convolutional Networks (TCNs) Attention-Based Models Self-Attention Mechanisms
Deep_Learning	Neural Machine Translation (NMT) Language Modeling Question Answering Systems Text Summarization Techniques Dialog Systems Conversational AI Reinforcement Learning in Robotics Sim-to-Real Transfer Robustness in Reinforcement Learning Hierarchical Reinforcement Learning
Deep_Learning	Imitation Learning Inverse Reinforcement Learning Continuous Control Problems Exploration Strategies in RL Reward Shaping Curriculum Learning in RL Hierarchical Policy Learning Policy Networks Value Networks Hierarchical Q-Learning
Deep_Learning	Deep Learning in Healthcare Image Analysis in Medical Diagnostics Genomic Data Analysis Drug Discovery with Deep Learning Deep Learning for Finance Algorithmic Trading Fraud Detection Sentiment and Opinion Mining Deep Learning in Autonomous Vehicles Object Tracking
Deep_Learning	Simultaneous Localization and Mapping (SLAM) Path Planning Algorithms Deep Learning for Robotics Manipulation and Grasping Robot Perception Systems Natural Language Interfaces Augmented Reality and Deep Learning Virtual Reality Applications Generative Models in Art and Design Ethics and Fairness in AI
Deep_Learning	AI Policy and Governance AI in Social Good Initiatives Future Trends in AI Research Quantum Computing and Deep Learning Neuromorphic Computing Biological Inspiration in AI Cross-Domain Applications Scalable AI Infrastructure AI and Sustainability AI in Space Exploration

Deep_Learning
Question	Option A	Option B	Option C	Option D

Time_Series_Analysis         Computer_Vision         CNN         RNN         Transfer_learning         NLP