Concatenation of all combinations of words

Given a string s and some strings words of the same length. Find all the starting positions of the substrings in s that can be formed by concatenating all the strings in words. Note that the substrings must exactly match the strings in words, and there can be no other characters in the middle, but there is no need to consider the order of the … Continue reading Concatenation of all combinations of words

Automatic code generator for training Reinforcement Learning policies

Generate custom template code to train you reinforcement learning policy using a simple web UI built with streamlit. It includes different environments and can be expanded to support multiple policies and frameworks with an high level of flexible hyperparameters customization. The generated code can be easily downloaded as .py file or Jupyter Notebook so to immediately start training your model or use it as a baseline … Continue reading Automatic code generator for training Reinforcement Learning policies

How Genify used a Transformer-based model to build a recommender system that outperforms industry benchmarks

The rapid ascension of AI, and more recently of deep learning, comported a succession of many breakthroughs in the field of computer science. These have had a profound impact on both the academic and the business world. In particular, modern deep learning techniques applied to the pre-existing concept of recommender systems has given birth to a new, superior class of neural recommender systems, which are … Continue reading How Genify used a Transformer-based model to build a recommender system that outperforms industry benchmarks

Genify’s experience testing Amazon Personalize: learnings and limitations

Challenges of machine learning Machine learning is a complex field that borrows elements from different areas such as computer science, algebra and statistics. Hence, it is not immediate, even for experts in the field, to build strong machine learning models to solve predefined task. Furthermore, those models should also be optimized with a time-consuming and repetitive hyper-parameters search in order to find the best set … Continue reading Genify’s experience testing Amazon Personalize: learnings and limitations

SeqGAN: text generation with generative models

In this post we propose to review recent history of research in the Natural Language Generation (NLG) tasks of the Natural Language Processing domain. Realistic human-like language generation has been a challenge for researches that has recently come into greater focus with the release of large neural models for NLP like the GPT and BERT models. In this post we propose to focus ourselves on … Continue reading SeqGAN: text generation with generative models

How I prepared an Elite Super Spartan Race

There’s nothing mediocre about this middle distance race. The Spartan Super offers the ideal blend between distance and speed. Offering racers a true athletic test. If you consider yourself a more seasoned athlete determined to push beyond excuses, you just might have the mettle for a Spartan Super. Serving up 25+ Spartan Obstacles and 10+km of rugged terrain, the Spartan Super spares no one. Developed … Continue reading How I prepared an Elite Super Spartan Race

Min-max in array

Given an array v of n numbers, where n=2k, k>0 be a natural number, find the minimum and maximum element in v. There are no assumptions regarding the orders of the elements of v. A basic iterative approach would require 2(n-1) comparisons (n-1 comparisons to find the minimum and n-1 comparisons to find the maximum). However, your program MUST perform at most 3/2n-1 comparisons. Difficulty: … Continue reading Min-max in array

K-th smallest element in unsorted array

Given an array v of distinct numbers, and a number k where k is smaller than the size of v, find the k-th smallest element in the array. A simple solution would be first sorting the array in growing order and than selecting the k-th element which can be done in θ(n logn). However, your program MUST run in θ(n) on average. Difficulty: Medium. Input There … Continue reading K-th smallest element in unsorted array

Adversarial policies: attacking TicTacToe multi-agent environment

In a previous post we discussed about the possibility for an attacker to fool image classification models by injecting adversarial noise directly to the input images. Similarly, in this post we are going to see how is it possible to attack deep reinforcements learning agents on multi-agent environments (where two or more agents interact within the same environment) such that one or more agents are … Continue reading Adversarial policies: attacking TicTacToe multi-agent environment

Defence methods for image adversarial attacks

In the previous post we reviewed some well-known methods for black-box decision-based adversarial attacks where the adversary has no knowledge about the victim model except for its discrete hard-label predictions, thus gradient-based methods become ineffective but simple random-walk based methods such as the Boundary Attack can still represent a threat even under these particular settings. Now that we have introduced both white and black-box attacks … Continue reading Defence methods for image adversarial attacks