Deep Learning Course in Hyderabad

Deep Learning Training In Hyderabad

Datajango Provides end to end Deep Learning Course with 100% Industry Ready code examples in Hyderabad. The course we will cover all necessary concepts to make a successful Data Scientist. The concepts we cover are Deep Neural Networks, Convolutional Neural Networks,Computer Vision,Natural Language Processing& Information Retrieval with Gensim, SpaCy and NLTK, Recurrent Neural Networks for Text Analysitcs.

Course Location Mode of Class Duration
Deep learning & NLP Hyderabad Class-Room/Online 3 Months

Deep Learning and Natural Language Processing Course Syllabus

Section – I Deep Neural Networks

Linear Regression Gradient Descent (Batch, Stochastic and Mini-Batch)

a. Forward propagation
b. Back propagation

a. Layers of a Deep Neural Network
b. Back propagation
c. Activation Functions (Sigmoid, Tanh, ReLU, Leaky ReLU, Softmax)

a. Construction Phase
i. tf.Variable
ii. tf.constant
iii. tf.placeholder
iv. Tensor reshape, slice, type cast
v. Variable collections - Global, Local, Trainable
vi. Initializing Variables
b. Execution Phase
c. Linear Regression with TensorFlow

Build hand written digit recognition model with TensorFlow

a. l1, l2 regularization
b. Dropout regularization

a. Weight initializations (He/Xavier initialization)

a. Momentum - Exponentially weighted moving average
b. Gradient Descent with Momentum
c. Gradient Descent with RMSProp (Root Mean Squared Propagation)
d. Gradient Descent with ADAM (Adaptive Momentum Estimation)
e. Batch Normalization

Section – II CNN (Convolutional Neural Networks)

Convolution and Edge Detection

Padding, Striding Convolutions

a. Edge Detection
b. Padding
c. Stride
d. Pooling

ResNets (CNN build with Residual Block)

Transfer Learning

Data Augmentation

  1. Object Location
  2. Intersection over Union
  3. Anchor Boxes
  4. Normax Suppression
  5. YOLO Algorithm
  6. Object Detection
  7. Face Verification

Section – III NLP (Natural Language Processing) & Information Retrieval with Gensim, SpaCy and NLTK

  1. Biword index
  2. Positional index

  1. SoundX algorithm
  2. Isolated words
    1. Edit Distance
    2. Weighted edit distance
  • N-Gram overlap (Jaccard coefficient)
  1. Context sensitive

  1. Term Frequency, Weighted Term Frequency, Inverse Document Frequency
  2. TF-IDF Scoring
  3. Euclidian distance
  4. Cosine similarity

  1. Singular Value Decomposition
  2. Latent Dirichlet Allocation (LDA)
  3. Latent Semantic Analysis

Word2vec (BoW, Skip Gram), GloVe, Doc2vec

Section – IV Recurrent Neural Networks for Text Analysitcs

Bidirectional Recurrent Neural Networks

Gated Recurrent Units

Long Short-Term Memory (LSTM)

Auto Encoders

TBD – RNN solutions for text problems