Old portfolio: Link

Mini Thesis at Institute of General Mechanics at RWTH Aachen University, Germany.

• ”Combine an Artificial Neural Network with an UMAT subroutine to replace a Chaboche Viscoplastic Constitutive Law in Abaqus.” Sequence to sequence learning using LSTM and Neural Networks. Visaulization using TensorBoard.

TensorFlow implementation to decipher sign language

• Repository

Navier-Stokes Equations using Python

• Repository

Optimization: Mini batch gradient descent with momentum and Adam mode

• Repository

Word2Vec using TensorFlow using dummy data

• Repository

He et al (2015) Initialization for Neural Networks

• Repository

Gradient Checking Algorithm

• Repository

Poppy Humanoid Robot

• Contribution to the open source platform of interactive 3D printed humanoid robots.

• https://www.poppy-project.org

• Video:
  

Football Corporation Goalkeeper Position Recommendation

• Repository

ABB IRB 7600-340 Robot visualization in VR and 3D mode using JavaScript (Ongoing)

Logistic regression to recognize cats

• Repository

Softmax Linear Classifier using 2 NN for visual recognition

• Cross Entropy Loss Function
• Repository

Recommendation System

• Recommendation System: Collaborative and Content-based; NumPy,SciPy, LightFM, OpenMP, Weighted Approximate-Rank Pairwise, Gradient Descent, Compressed Sparse Row Format; MovieLens: GroupLens Research Site (University of Minnesota)
• Repository

• https://movielens.org/

  def sample_recommendation(model, data, user_ids):
  # number of users and movies in training data
  n_users, n_items = data['train'].shape
  # generate recommendations for each user we input
  for user_id in user_ids:
      # movies they already like
      known_positives = data['item_labels'][data['train'].tocsr()[user_id].indices]
  
      # movies our model predicts they will like
      scores = model.predict(user_id, np.arange(n_items))
  
      # rank them in order of most liked to the least
      top_items = data['item_labels'][np.argsort(-scores)]
  
      # print out the results
      print('User %s' % user_id)
      print('Known positives:')
  
      for x in known_positives[:3]:
          print('        %s' % x)
  
      print('Recommended:')
  
      for x in top_items[:3]:
          print('         %s' % x)
  

Supervised learning with 5 layer deep neural network using ReLU for image classification.

• Repository

Planar data classification

• Repository

Dymola Systems Simulation of a Washing Machine

• Video: