AD3501 DEEP LEARNING

Stuff Sector
      Prepared by  
      Santhosh (Admin) 

Important questions 
share it a link alone

Don't share as screenshot kind request

UNIT I DEEP NETWORKS BASICS
 
Vectors, Matrices and tensors; Probability Distribution
 Gradientbased Optimization, ML (Overfitting and underfitting)***
 Bias and variance  Stochastic gradient  descent
 Challenges motivating deep learning**
Deep feedforward networks,Optimization.***

UNIT II CONVOLUTIONAL NEURAL NETWORKS 

Convolution Operation, Sparse Interactions *** Equivariance,  Pooling, Strided 
Transposed and dilated convolutions
Nonlinearity Functions, Loss Functions*** Regularization , Gradient Computation.***

UNIT III RECURRENT NEURAL NETWORKS

 RNN Design Patterns, Acceptor, Encoder,Transducer
  Bidirectional RNN,  Sequence to Sequence RNN*** 
 Deep Recurrent Networks, Recursive Neural Networks***
Long Term Dependencies,Gated Architecture: LSTM.

UNIT IV MODEL EVALUATION 

Baseline Models , Automatic Hyperparameter 
Grid search , Random search**
Debugging strategies.*** May be part c
 
UNIT V AUTOENCODERS AND GENERATIVE MODELS 

Undercomplete ,Regularized autoencoders ** rare 
Stochastic encoders and decoders ***
Learning Abt and Variational autoencoders **
Generative adversarial networks.

Don't share as screenshot


**Most important topic ,Can get good marks but read all topic thoroughly

PART-C

1.Compulsory Questions {a case study where the student will have to read and analyse the subject }
mostly asked 3,5unit (OR) a situation given and you have to answer on your own

don't waste my hardwork and valuable time

As Engineer i think you know how to respect another
Share it as link alone . don't share it as screenshot or any text material if u found this anywhere kindly report me . #Admin   WhatsApp

Contact uS *These questions are expected for the exams This may or may not be asked for exams
    All the best.... from admin Santhosh

          Thanks for your love and support guys keep supporting and share let the Engineers know about Us and leave a comment below for better improvements 
If there is any doubt feel free to ask me I will clear if I can or-else I will say some solutions ..get me through WhatsApp for instant updates                                                     _-Stuff Sector

Syllabus

 UNIT I DEEP NETWORKS BASICS

Linear Algebra: Scalars -- Vectors -- Matrices and tensors; Probability Distributions -- Gradientbased Optimization – Machine Learning Basics: Capacity -- Overfitting and underfitting --

Hyperparameters and validation sets -- Estimators -- Bias and variance -- Stochastic gradient

descent -- Challenges motivating deep learning; Deep Networks: Deep feedforward networks;

Regularization -- Optimization.

UNIT II CONVOLUTIONAL NEURAL NETWORKS

Convolution Operation -- Sparse Interactions -- Parameter Sharing -- Equivariance -- Pooling --

Convolution Variants: Strided -- Tiled -- Transposed and dilated convolutions; CNN Learning:

Nonlinearity Functions -- Loss Functions -- Regularization -- Optimizers --Gradient Computation.

UNIT III RECURRENT NEURAL NETWORKS

Unfolding Graphs -- RNN Design Patterns: Acceptor -- Encoder --Transducer; Gradient

Computation -- Sequence Modeling Conditioned on Contexts -- Bidirectional RNN -- Sequence to

Sequence RNN – Deep Recurrent Networks -- Recursive Neural Networks -- Long Term

Dependencies; Leaky Units: Skip connections and dropouts; Gated Architecture: LSTM.

UNIT IV MODEL EVALUATION

Performance metrics -- Baseline Models -- Hyperparameters: Manual Hyperparameter -- Automatic

Hyperparameter -- Grid search -- Random search -- Debugging strategies.

UNIT V AUTOENCODERS AND GENERATIVE MODELS

Autoencoders: Undercomplete autoencoders -- Regularized autoencoders -- Stochastic encoders

and decoders -- Learning with autoencoders; Deep Generative Models: Variational autoencoders –

Generative adversarial networks.

Santhosh (Admin)

TO THE ENGINEER FOR THE ENGINNEER BY AN ENGINEER Kindly join Us on social media's link at the top corner

Post a Comment

Please Select Embedded Mode To Show The Comment System.*

Previous Post Next Post